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

    Neuronpedia

    Jacobian LensNEW
    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. 20556
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or processes involving data manipulation or organizational activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to financial implications and economic activities

    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
    .",
    -0.67
    estine
    -0.61
    ?",
    -0.58
    .?
    -0.57
    committee
    -0.56
    GROUP
    -0.56
    oln
    -0.55
    ,,,,
    -0.54
    ocument
    -0.53
    eva
    -0.53
    POSITIVE LOGITS
    ãĥĩãĤ£
    0.60
     sonic
    0.49
     winds
    0.49
    ãĤ³
    0.48
    ãĥ¥
    0.48
    OAD
    0.47
    ãĤ°
    0.47
    ãĥĨãĤ£
    0.47
     nods
    0.47
     loader
    0.46
    Activations Density 1.041%

    No Known Activations