© 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. 3-RES-JB
    11. 8215
    Prev
    Next
    INDEX
    Explanations

    mentions of instructions or advice

    oai_token-act-pair · gpt-3.5-turbo

    contractions of the word "are" and related verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proport
    -0.34
    querque
    -0.34
    ividual
    -0.33
    ãĥ¼ãĥĨ
    -0.32
     sprung
    -0.31
     degraded
    -0.31
    allery
    -0.30
     undermin
    -0.30
    milo
    -0.30
     lasted
    -0.29
    POSITIVE LOGITS
    PLA
    0.40
    APD
    0.39
    COM
    0.36
    ATT
    0.36
    IPS
    0.35
    BT
    0.35
    mb
    0.35
    resp
    0.34
    NetMessage
    0.34
    IP
    0.33
    Activations Density 1.943%

    No Known Activations