© 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. 24138
    Prev
    Next
    INDEX
    Explanations

    specific instances or occurrences of events, especially those involving medical conditions, legal matters, or community concerns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cases" in relation to various discussions or analyses

    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
    roe
    -0.73
    rients
    -0.71
     livest
    -0.70
     streng
    -0.68
    BN
    -0.68
    owered
    -0.67
    obil
    -0.65
    atomic
    -0.64
    DES
    -0.64
    rongh
    -0.63
    POSITIVE LOGITS
    cases
    1.15
     cases
    0.97
    cale
    0.84
    manship
    0.76
     Cases
    0.74
    rooms
    0.74
    paces
    0.74
    afety
    0.73
    backs
    0.73
    hooting
    0.72
    Activations Density 0.015%

    No Known Activations