© 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. 8-RES-JB
    11. 16906
    Prev
    Next
    INDEX
    Explanations

    occurrences of exclamations and informal expressions

    oai_token-act-pair · gpt-3.5-turbo

    unusual or emotive punctuation and formatting within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     targeted
    -0.85
    mercial
    -0.82
     advertisers
    -0.78
     voting
    -0.72
     centrally
    -0.71
     electorate
    -0.70
    olicy
    -0.69
     benefits
    -0.69
    abase
    -0.68
     nonpartisan
    -0.67
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.18
    âĶĢâĶĢâĶĢâĶĢ
    1.10
    laughs
    1.06
    laugh
    0.93
    âĹ
    0.87
    Brend
    0.86
    sung
    0.85
    âĶĢ
    0.83
    ~
    0.82
    dro
    0.81
    Activations Density 0.408%

    No Known Activations