© 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. 39814
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms and references

    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
    385
    +0.05
    0.6%
    699
    +0.04
    0.5%
    316
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.05
    0.01
    308
    +0.04
    0.12
    731
    +0.04
    0.09
    Negative Logits
    emouth
    -0.34
    esses
    -0.29
    ovo
    -0.29
     Advertisement
    -0.29
    eness
    -0.27
     Amos
    -0.27
    iqueness
    -0.26
    jee
    -0.25
     Mata
    -0.25
     Carbuncle
    -0.24
    POSITIVE LOGITS
    §
    0.40
    rust
    0.29
    GAN
    0.27
    arse
    0.27
    oral
    0.26
    fa
    0.26
    ARS
    0.26
    arist
    0.26
    armor
    0.25
    Effective
    0.25
    Activations Density 6.169%

    No Known Activations