© 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. 22513
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities, possibly related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns associated with organizations, groups, and military entities

    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
     amen
    -0.68
    Houston
    -0.65
     deductible
    -0.63
    bilt
    -0.62
     teamwork
    -0.61
    asonable
    -0.60
    scl
    -0.59
     Houston
    -0.59
     nausea
    -0.59
     predetermined
    -0.58
    POSITIVE LOGITS
     Orchestra
    0.84
     Alm
    0.79
    oglu
    0.77
    ÄŁ
    0.75
     abroad
    0.71
    hops
    0.71
    avi
    0.69
    eri
    0.69
    orate
    0.68
    ãĥķãĤ©
    0.67
    Activations Density 0.493%

    No Known Activations