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. 6-RES-JB
    6. 17915
    Prev
    Next
    INDEX
    Explanations

    phrases related to support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions involving support or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.70
     Schwar
    -0.64
     Takeru
    -0.63
     printers
    -0.62
     denomin
    -0.60
    imov
    -0.60
    die
    -0.57
     carriage
    -0.56
    SPONSORED
    -0.56
     millisec
    -0.56
    POSITIVE LOGITS
    olo
    0.82
    olicy
    0.78
    rison
    0.75
    ĺħ
    0.74
    OPER
    0.72
    amphetamine
    0.70
    xon
    0.69
    inion
    0.68
    igious
    0.68
    earance
    0.67
    Activations Density 0.044%

    No Known Activations