© 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. 714
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of places and people

    oai_token-act-pair · gpt-4-turbo

    mentions of the Dead Sea

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations or significant entities

    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
    iage
    -0.86
    iso
    -0.85
    ieth
    -0.83
    inarily
    -0.80
    enium
    -0.75
     payable
    -0.73
    ety
    -0.72
    ivities
    -0.71
    aph
    -0.70
    essee
    -0.70
    POSITIVE LOGITS
     Labyrinth
    0.72
    Lear
    0.72
    ç¥ŀ
    0.70
     Typh
    0.67
     dab
    0.65
    Lie
    0.65
     XCOM
    0.64
     masturbation
    0.64
     facilit
    0.64
     Dahl
    0.64
    Activations Density 0.000%

    No Known Activations