© 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. 7-RES-JB
    11. 18636
    Prev
    Next
    INDEX
    Explanations

    financial terms and holdings

    oai_token-act-pair · gpt-3.5-turbo

    nouns and phrases related to quantitative measures or entities related to groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amera
    -0.66
     Basin
    -0.58
     ancest
    -0.56
     consortium
    -0.55
    elaide
    -0.54
     detrim
    -0.53
    estern
    -0.52
    issance
    -0.52
    iverse
    -0.51
     kittens
    -0.51
    POSITIVE LOGITS
     thereof
    1.23
     of
    1.14
     Of
    0.95
    of
    0.94
    Of
    0.93
     OF
    0.92
    ghai
    0.82
    OF
    0.72
    arak
    0.68
    luster
    0.67
    Activations Density 0.657%

    No Known Activations