© 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. 23603
    Prev
    Next
    INDEX
    Explanations

    activities involving work or play

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various aspects of conflict and societal issues

    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
    pload
    -0.64
     Instr
    -0.63
    eday
    -0.61
     Azerb
    -0.58
    ãĥĩãĤ£
    -0.58
    Legend
    -0.57
    tk
    -0.56
    amaz
    -0.56
    ãĥ¼ãĥĨãĤ£
    -0.56
    umbn
    -0.55
    POSITIVE LOGITS
     alike
    1.31
     respectively
    1.06
     collide
    0.68
     are
    0.65
    ↵↵
    0.65
     combine
    0.62
    ¶
    0.61
    ;;;;;;;;;;;;
    0.60
     (%)
    0.59
     were
    0.58
    Activations Density 0.339%

    No Known Activations