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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 22643
    Prev
    Next
    INDEX
    Explanations

    multi-syllable names that may represent diverse cultural or political references

    oai_token-act-pair · gpt-3.5-turbo

    names of people or entities, particularly those related to specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MW
    -0.77
    LY
    -0.75
    MR
    -0.74
    LIN
    -0.71
     Monthly
    -0.70
    ML
    -0.70
    LAN
    -0.70
    writer
    -0.70
    itable
    -0.69
    lad
    -0.68
    POSITIVE LOGITS
    gio
    1.13
    abba
    0.91
    agn
    0.79
    ĸļ
    0.78
    ascus
    0.78
    acca
    0.75
    rals
    0.75
    orsi
    0.71
    riction
    0.70
    uters
    0.66
    Activations Density 0.034%

    No Known Activations