© 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. 15683
    Prev
    Next
    INDEX
    Explanations

    academic titles and positions in research settings

    oai_token-act-pair · gpt-3.5-turbo

    academic titles and affiliations related to research

    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
     decency
    -0.76
     softer
    -0.73
     craz
    -0.72
     inconven
    -0.68
    AAF
    -0.68
     brav
    -0.68
     repe
    -0.67
     corrid
    -0.67
     disapp
    -0.66
     frust
    -0.66
    POSITIVE LOGITS
    inguished
    0.92
    doctoral
    0.91
    uates
    0.89
     Faculty
    0.86
     IEEE
    0.84
    lished
    0.83
     doctoral
    0.82
    study
    0.78
    lies
    0.78
     dissertation
    0.77
    Activations Density 0.147%

    No Known Activations