© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10945
    Prev
    Next
    INDEX
    Explanations

    action verbs associated with decisions or interventions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs indicating control or change

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

    No Comments

    Negative Logits
     Extrem
    -0.69
    iege
    -0.67
    é¾į
    -0.64
     mole
    -0.64
    edge
    -0.62
     Passage
    -0.60
    REP
    -0.59
    vae
    -0.59
     Pione
    -0.57
    JUST
    -0.57
    POSITIVE LOGITS
    able
    0.97
    ings
    0.92
    ably
    0.88
    ardless
    0.82
     yourselves
    0.81
    ability
    0.78
    ingly
    0.75
     yourself
    0.75
    ables
    0.73
    atron
    0.71
    Activations Density 0.279%

    No Known Activations