© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23207
    Prev
    Next
    INDEX
    Explanations

    words related to specific places or areas

    oai_token-act-pair · gpt-3.5-turbo

    words related to forms of servitude or belonging

    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
     Late
    -0.70
     polit
    -0.69
     newspaper
    -0.67
     Kinnikuman
    -0.67
     ty
    -0.65
     event
    -0.64
     late
    -0.64
     capacity
    -0.63
     Nit
    -0.63
     Kit
    -0.62
    POSITIVE LOGITS
    aves
    4.84
    ave
    2.45
    aved
    2.37
    aving
    2.25
    avery
    1.80
    avers
    1.59
    aver
    1.34
    avement
    1.19
    oves
    1.16
    avin
    1.15
    Activations Density 0.012%

    No Known Activations