© 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. 20166
    Prev
    Next
    INDEX
    Explanations

    information related to specific individuals, their occupations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and their functions

    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
     proved
    -0.67
     barg
    -0.57
     morphed
    -0.57
     matured
    -0.56
     misogyn
    -0.56
    utterstock
    -0.56
     unquestion
    -0.55
     proves
    -0.55
     predetermined
    -0.55
    emort
    -0.55
    POSITIVE LOGITS
    >.
    0.78
    veland
    0.74
    eous
    0.68
     Southwest
    0.65
    _.
    0.64
    .).
    0.62
    esters
    0.62
     Merchants
    0.62
    heastern
    0.62
    ].
    0.60
    Activations Density 0.647%

    No Known Activations