© 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. 2-RES-JB
    11. 3916
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.71
    editor
    -0.63
     comr
    -0.62
    EStream
    -0.61
    Orig
    -0.61
    kell
    -0.60
    ?????-
    -0.60
     beh
    -0.60
    ROR
    -0.59
    ACTION
    -0.58
    POSITIVE LOGITS
     percent
    1.08
    %"
    0.98
    %,
    0.90
    %
    0.90
    %.
    0.87
    %;
    0.85
     pounds
    0.83
     Percent
    0.80
    ½
    0.80
     inches
    0.79
    Activations Density 0.483%

    No Known Activations