© 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. 0-RES-JB
    11. 22351
    Prev
    Next
    INDEX
    Explanations

    phrases related to the names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of listed numerical values or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irlf
    -0.70
    ividual
    -0.70
    sbm
    -0.66
    ozyg
    -0.60
    itially
    -0.60
    ecause
    -0.59
    ;;;;;;;;;;;;
    -0.58
    umenthal
    -0.58
    ancial
    -0.57
    athered
    -0.57
    POSITIVE LOGITS
    ,
    1.41
    ,...
    1.04
    ,[
    0.82
    ;
    0.72
    ,,
    0.71
    !,
    0.69
    ,—
    0.68
    ,.
    0.66
    ®,
    0.65
    :
    0.65
    Activations Density 1.533%

    No Known Activations