© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 19810
    Prev
    Next
    INDEX
    Explanations

    words related to confession or acceptance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "admit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.72
    à¦
    -0.69
    seed
    -0.67
    andel
    -0.66
    bul
    -0.65
    GROUP
    -0.65
    irrel
    -0.65
    colo
    -0.64
    govtrack
    -0.63
    atic
    -0.62
    POSITIVE LOGITS
     wrongdoing
    0.86
     defeat
    0.76
     admitting
    0.72
     guilt
    0.70
     admits
    0.70
     admitted
    0.67
     apologized
    0.67
     negligence
    0.65
     Dempsey
    0.64
     conced
    0.63
    Activations Density 0.049%

    No Known Activations