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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32190
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to oneself

    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
    46
    +0.06
    0.5%
    324
    +0.05
    0.4%
    701
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.06
    0.08
    48
    +0.05
    0.09
    564
    +0.05
    0.09
    Negative Logits
    Avg
    -0.37
     Amend
    -0.35
     Learns
    -0.34
     racket
    -0.33
    tackle
    -0.33
     intens
    -0.33
     Noon
    -0.32
     [+
    -0.31
    mus
    -0.31
     Antar
    -0.31
    POSITIVE LOGITS
    selves
    0.60
    ridges
    0.56
    ortium
    0.50
    theless
    0.49
    ridge
    0.46
    destruct
    0.45
    self
    0.44
     selves
    0.43
    ault
    0.42
    enes
    0.42
    Activations Density 4.788%

    No Known Activations