© 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. 3047
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and political figures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and sentence-ending structures

    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
     dra
    -0.78
     commissions
    -0.74
     harvest
    -0.71
     waterfall
    -0.71
     upstream
    -0.70
     Aval
    -0.70
    ĸļ
    -0.70
     downstream
    -0.69
     casc
    -0.68
     payroll
    -0.68
    POSITIVE LOGITS
    Asked
    1.82
    SPONSORED
    1.76
    Speaking
    1.72
    Refer
    1.72
    Calling
    1.66
    However
    1.57
    He
    1.55
    Regarding
    1.54
    His
    1.53
    Specifically
    1.53
    Activations Density 0.482%

    No Known Activations