Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3276
    Prev
    Next
    INDEX
    Explanations

    phrases related to pairs or duplicates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic downturns and recessions

    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
     uncond
    -0.65
     Mandal
    -0.61
     Sabha
    -0.59
     Papua
    -0.59
     Adin
    -0.59
    ################
    -0.59
     Cth
    -0.58
     sap
    -0.57
     breeze
    -0.55
     Kimmel
    -0.55
    POSITIVE LOGITS
    ammy
    1.09
    eds
    0.73
    fect
    0.71
    edly
    0.71
    äºĶ
    0.69
    headed
    0.68
    fig
    0.67
    edged
    0.67
    rencies
    0.66
    imester
    0.65
    Activations Density 0.104%

    No Known Activations