© 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. 6-RES-JB
    11. 4227
    Prev
    Next
    INDEX
    Explanations

    instances where something is mentioned as being barely there or in a weak state

    oai_token-act-pair · gpt-3.5-turbo

    instances of minimal existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.71
    ãĥ¤
    -0.66
     Parenthood
    -0.65
     Types
    -0.64
     Origins
    -0.61
    uments
    -0.60
     Values
    -0.59
    idon
    -0.59
    afort
    -0.58
     cornerstone
    -0.58
    POSITIVE LOGITS
     escaped
    0.84
     scratched
    0.83
     survived
    0.82
    icable
    0.81
    Ń·
    0.80
     graz
    0.79
     succeeded
    0.75
     scraping
    0.75
    clad
    0.75
    WARE
    0.74
    Activations Density 0.012%

    No Known Activations