© 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. 11280
    Prev
    Next
    INDEX
    Explanations

    references to legal or political events involving specific locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" and its variations in various contexts

    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
    !/
    -0.73
    items
    -0.71
    Edit
    -0.71
    ATURES
    -0.70
    ?!
    -0.70
    âĿ
    -0.70
    MSN
    -0.66
    !!!!!
    -0.66
    !:
    -0.66
    lest
    -0.65
    POSITIVE LOGITS
    rouse
    1.05
     lot
    0.93
     handful
    0.92
     bunch
    0.92
     decade
    0.89
     sizeable
    0.89
     lengthy
    0.87
     sizable
    0.86
     plethora
    0.86
     mammoth
    0.85
    Activations Density 0.950%

    No Known Activations