© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 8150
    Prev
    Next
    INDEX
    Explanations

    names of individuals, potentially in a legal or official context

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns, particularly those that may relate to a story or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompan
    -0.91
     eleph
    -0.81
     DIRECT
    -0.67
     teasp
    -0.65
     parasitic
    -0.64
     IMP
    -0.63
     conserv
    -0.63
     transitioning
    -0.62
     GOODMAN
    -0.62
     carbohyd
    -0.60
    POSITIVE LOGITS
    a
    1.22
    e
    1.15
    o
    1.14
    y
    1.05
    aq
    1.04
    i
    1.02
    ic
    1.02
    er
    1.00
    al
    0.99
    u
    0.98
    Activations Density 0.245%

    No Known Activations