© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3192
    Prev
    Next
    INDEX
    Explanations

    discussions related to academic research and political debates

    oai_token-act-pair · gpt-3.5-turbo

    information related to academic institutions and political contexts

    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
    anwhile
    -0.68
    leness
    -0.54
     Palest
    -0.48
     reciproc
    -0.47
     Decay
    -0.46
    æ©
    -0.45
    lict
    -0.44
    reditary
    -0.44
     reciprocal
    -0.44
     Kappa
    -0.44
    POSITIVE LOGITS
     )]
    0.79
    DCS
    0.64
    >)
    0.64
     ):
    0.62
    ãĢij
    0.60
     acronym
    0.60
    ):
    0.58
    )]
    0.56
     ])
    0.56
    *)
    0.55
    Activations Density 1.845%

    No Known Activations