© 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. 18712
    Prev
    Next
    INDEX
    Explanations

    phrases related to research, surveys, experiments, and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to research findings or results

    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
    inks
    -0.83
    ener
    -0.76
    orthy
    -0.73
    iste
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    resses
    -0.66
    eners
    -0.65
    username
    -0.64
     tops
    -0.63
    forward
    -0.63
    POSITIVE LOGITS
     tests
    0.92
     investigation
    0.92
     investigations
    0.91
     autopsy
    0.86
     examinations
    0.85
     interviews
    0.84
     disse
    0.84
     preliminary
    0.83
     negotiations
    0.82
     surveys
    0.80
    Activations Density 0.195%

    No Known Activations