© 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. 9-RES-JB
    11. 13206
    Prev
    Next
    INDEX
    Explanations

    mentions of memberships, contributions, and affiliations in various organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    mentions of membership in organizations or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bang
    -0.71
    zyk
    -0.71
     sucked
    -0.70
    fecture
    -0.69
     alive
    -0.68
     paused
    -0.65
     fuelled
    -0.65
     limitation
    -0.65
    Asked
    -0.64
    nels
    -0.64
    POSITIVE LOGITS
     numerous
    0.93
     prestigious
    0.81
     Physicians
    0.80
     Alter
    0.80
     Honor
    0.80
    ospons
    0.80
    -+-+
    0.80
     various
    0.79
     Advisory
    0.79
     several
    0.78
    Activations Density 0.251%

    No Known Activations