© 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. 20270
    Prev
    Next
    INDEX
    Explanations

    verbs related to activities or actions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to actions and responsibilities

    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
    Bride
    -0.73
    Nich
    -0.70
    Afee
    -0.68
    Marie
    -0.66
    \\\\\\\\
    -0.65
    Benef
    -0.65
    Myth
    -0.64
    Aren
    -0.64
    Universal
    -0.64
    FN
    -0.64
    POSITIVE LOGITS
     english
    0.84
    xual
    0.67
     dont
    0.64
     sd
    0.62
     ><
    0.59
     americ
    0.59
     dope
    0.58
     sucks
    0.58
    nt
    0.57
     flair
    0.57
    Activations Density 0.208%

    No Known Activations