© 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. 9-RES-JB
    11. 9054
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or brand names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intermedi
    -0.80
     Malone
    -0.78
     Assass
    -0.74
    acion
    -0.72
    interstitial
    -0.71
     Antar
    -0.71
    agascar
    -0.68
     Instr
    -0.68
     sarc
    -0.68
     obser
    -0.67
    POSITIVE LOGITS
    W
    1.20
    w
    1.19
    WM
    1.15
    WC
    1.10
    WF
    1.08
    WA
    1.08
    ws
    1.07
    ww
    1.07
    WP
    1.07
    WS
    1.06
    Activations Density 0.401%

    No Known Activations