© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39654
    Prev
    Next
    INDEX
    Explanations

    news related to different events occurring in various locations

    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
    640
    +0.19
    1.2%
    447
    +0.12
    0.8%
    372
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.53
    64
    +0.12
    -0.25
    373
    +0.08
    -0.23
    Negative Logits
     scept
    -0.58
    heit
    -0.55
    umni
    -0.54
    boro
    -0.54
     dissu
    -0.52
     favour
    -0.51
     diseng
    -0.50
     tempted
    -0.50
     endeav
    -0.49
    utical
    -0.49
    POSITIVE LOGITS
    Owner
    0.61
    PHOTOS
    0.61
    Specifically
    0.61
    WARD
    0.61
    SHARE
    0.60
    SEE
    0.59
    FTWARE
    0.58
    ccording
    0.55
    READ
    0.54
    His
    0.53
    Activations Density 16.103%

    No Known Activations