© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4865
    Prev
    Next
    INDEX
    Explanations

    technical details related to data storage and processing, including measurements like gigabytes (GB) and kilobytes (KB)

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    211
    +0.13
    0.7%
    288
    +0.10
    0.6%
    635
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.13
    0.08
    504
    +0.10
    0.07
    635
    +0.09
    0.06
    Negative Logits
    terday
    -0.73
    ebus
    -0.69
    iment
    -0.68
    orship
    -0.67
    ocrats
    -0.67
    imity
    -0.64
    tenance
    -0.64
    unct
    -0.64
    ortium
    -0.61
    andr
    -0.60
    POSITIVE LOGITS
    UGE
    0.77
    ITS
    0.71
    FFER
    0.67
    RM
    0.65
    GB
    0.65
    BM
    0.65
    RAY
    0.64
    RI
    0.64
    DT
    0.63
    PP
    0.63
    Activations Density 7.047%

    No Known Activations