© 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. 24560
    Prev
    Next
    INDEX
    Explanations

    quotes or reported speech from individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements or quotations attributed to individuals

    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
    adies
    -0.69
     ILCS
    -0.68
    otin
    -0.66
    pend
    -0.60
    atible
    -0.59
    rafted
    -0.59
    oil
    -0.59
    oint
    -0.59
     pend
    -0.58
    Measure
    -0.58
    POSITIVE LOGITS
     sarcast
    1.07
     bluntly
    0.96
    terday
    0.83
     aloud
    0.82
     rhet
    0.76
     angrily
    0.76
     confidently
    0.76
     emphatically
    0.75
     bitterly
    0.73
     proudly
    0.71
    Activations Density 0.144%

    No Known Activations