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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19722
    Prev
    Next
    INDEX
    Explanations

    references to Irish-related entities or subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to the Irish community and culture

    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
    ĸļ
    -0.86
    eger
    -0.81
    PsyNetMessage
    -0.81
    isites
    -0.74
    iguous
    -0.74
    inson
    -0.74
    insula
    -0.74
    iage
    -0.73
    ularity
    -0.73
    nels
    -0.72
    POSITIVE LOGITS
    man
    0.92
    lander
    0.85
     Gael
    0.83
    men
    0.82
     moss
    0.82
    town
    0.81
     Catholic
    0.79
     Volunteers
    0.79
     Examiner
    0.78
     Catholics
    0.75
    Activations Density 0.014%

    No Known Activations