© 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. 8-RES-JB
    11. 22518
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to control, management, or influence over situations

    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
     narrated
    -0.66
    anse
    -0.64
    ials
    -0.62
    DragonMagazine
    -0.62
    essors
    -0.61
     ·
    -0.60
    raped
    -0.60
    nature
    -0.59
    rw
    -0.58
    ":["
    -0.55
    POSITIVE LOGITS
    creen
    0.77
    kered
    0.71
    ħĭ
    0.66
    querade
    0.66
    \\\\\\\\
    0.64
    ELY
    0.61
    vae
    0.61
     shoulders
    0.61
    ©¶æ¥µ
    0.60
    itial
    0.59
    Activations Density 0.365%

    No Known Activations