© 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. 17167
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "it" followed by some form of verb or verb phrase

    oai_token-act-pair · gpt-3.5-turbo

    references to unspecified subjects or situations that dominate the discussion

    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
     RTX
    -0.80
     Tories
    -0.73
    76561
    -0.70
     Pirates
    -0.69
     Held
    -0.67
    asts
    -0.66
    éļ
    -0.66
     Tiff
    -0.64
    eday
    -0.62
    shi
    -0.62
    POSITIVE LOGITS
     revolves
    0.83
     consists
    0.76
     contained
    0.72
     consisted
    0.71
     depends
    0.70
    IDENT
    0.68
     survives
    0.67
     involved
    0.66
     blame
    0.65
     charm
    0.65
    Activations Density 0.083%

    No Known Activations