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. 4482
    Prev
    Next
    INDEX
    Explanations

    words related to relationships and marital status

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wives and marital relationships

    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
     Flavoring
    -0.94
    é¾
    -0.71
    OLOG
    -0.69
     GOODMAN
    -0.69
     constitu
    -0.68
    EMS
    -0.67
     Edison
    -0.67
    oola
    -0.66
    Rush
    -0.66
     Spicer
    -0.65
    POSITIVE LOGITS
    hood
    1.07
    heses
    0.95
    hesis
    0.86
    hip
    0.84
    maid
    0.81
    liest
    0.78
    volent
    0.75
    less
    0.73
    doctor
    0.72
     groom
    0.72
    Activations Density 0.096%

    No Known Activations