© 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. 23979
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations related to politics or medicine

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and specific terms associated with influential entities or topics

    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
    teen
    -0.79
    ELL
    -0.65
    lly
    -0.65
    Bridge
    -0.65
    selected
    -0.63
    Cand
    -0.62
    ©¶æ
    -0.62
    low
    -0.61
    pend
    -0.61
     explan
    -0.60
    POSITIVE LOGITS
    azine
    0.85
    itude
    0.84
     Amph
    0.83
    atform
    0.82
    ific
    0.82
    iant
    0.75
    anca
    0.75
    ician
    0.74
    adiator
    0.74
    indal
    0.73
    Activations Density 0.025%

    No Known Activations