© 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. 7-RES-JB
    11. 17196
    Prev
    Next
    INDEX
    Explanations

    instances of falsely or wrongly claiming or accusing

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating falsehood or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soc
    -0.75
    soDeliveryDate
    -0.69
    iments
    -0.67
    RAW
    -0.66
    Legendary
    -0.65
    players
    -0.64
    player
    -0.60
    ilion
    -0.60
    href
    -0.59
    Reviewer
    -0.58
    POSITIVE LOGITS
     declare
    0.93
     reproduce
    0.93
     withdrew
    0.91
     demonstrate
    0.88
     engage
    0.87
     utilize
    0.87
     proclaim
    0.86
     resided
    0.86
     differentiate
    0.83
     entered
    0.83
    Activations Density 0.176%

    No Known Activations