© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5306
    Prev
    Next
    INDEX
    Explanations

    negative sentiments such as criticisms or concerns in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    503
    +0.15
    0.6%
    48
    +0.14
    0.5%
    578
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.15
    0.03
    251
    +0.14
    0.03
    48
    +0.13
    0.03
    Negative Logits
    hoe
    -0.98
    Downloadha
    -0.95
    anwhile
    -0.93
    £ı
    -0.83
    Nusra
    -0.80
    tone
    -0.79
     Ferr
    -0.75
    ãĥ¯ãĥ³
    -0.75
     chants
    -0.75
    bone
    -0.74
    POSITIVE LOGITS
    avorite
    1.07
    ortun
    1.04
    ancies
    1.02
    ortunate
    1.02
    ixed
    1.00
    athom
    1.00
    rost
    1.00
    avour
    0.99
    itted
    0.97
    iaries
    0.96
    Activations Density 0.225%

    No Known Activations