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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40012
    Prev
    Next
    INDEX
    Explanations

    instructions related to handling and storing medication capsules

    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
    480
    +0.42
    5.6%
    64
    +0.35
    4.7%
    481
    +0.29
    3.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.42
    0.50
    447
    +0.35
    0.51
    64
    +0.29
    -0.10
    Negative Logits
     [âĢ¦]
    -0.31
     âĢİ
    -0.28
    ↵Âł
    -0.26
     ....
    -0.25
     ......
    -0.23
    SPONSORED
    -0.23
     Âł Âł Âł Âł
    -0.23
     Âł Âł
    -0.23
     Âł
    -0.22
     ...
    -0.22
    POSITIVE LOGITS
    arger
    0.22
    APD
    0.21
    ItemTracker
    0.20
    umbn
    0.19
    arcity
    0.19
    ADRA
    0.19
    raid
    0.19
    apy
    0.18
    roman
    0.18
    arella
    0.18
    Activations Density 3.030%

    No Known Activations