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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 9026
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and governmental actions such as "remand", "categorical imperative", and "issuing an injunction."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government spending and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Headquarters
    -0.74
     Difficulty
    -0.71
     Powers
    -0.70
     Photographer
    -0.69
     Expend
    -0.67
     Finder
    -0.66
     Direction
    -0.66
    OHN
    -0.66
     Exit
    -0.65
     Cere
    -0.64
    POSITIVE LOGITS
    ingly
    0.94
    itating
    0.85
    anced
    0.84
    arse
    0.84
    kered
    0.84
    ably
    0.84
    antly
    0.84
    aded
    0.84
    ously
    0.83
    viously
    0.83
    Activations Density 0.261%

    No Known Activations