© 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. 8380
    Prev
    Next
    INDEX
    Explanations

    words related to installations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to institutions and institutional 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
    dress
    -0.79
     Tone
    -0.75
    berries
    -0.71
     KING
    -0.70
    tsky
    -0.68
    RANT
    -0.68
    UGH
    -0.65
    theless
    -0.63
     mustard
    -0.62
    ball
    -0.62
    POSITIVE LOGITS
    itutional
    1.36
    inct
    1.17
    alled
    1.08
    itute
    1.07
    itution
    1.05
    Inst
    1.03
     Inst
    1.00
    ellation
    0.92
    inst
    0.89
    urated
    0.85
    Activations Density 0.008%

    No Known Activations