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. 5-RES-JB
    6. 8221
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Bl" followed by a number, potentially suggesting the detection of a specific name or label in a text

    oai_token-act-pair · gpt-3.5-turbo

    the name or reference to a specific individual or entity, particularly "Bl" in various contexts

    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
     Occupations
    -0.87
    IUM
    -0.71
    HER
    -0.71
     WATCH
    -0.70
    OLOGY
    -0.69
    gerald
    -0.67
    UAL
    -0.64
    EStream
    -0.63
    xon
    -0.63
    PLIED
    -0.63
    POSITIVE LOGITS
    anche
    1.25
    itzer
    1.24
    asts
    1.15
    adder
    1.10
    ocking
    1.10
    anco
    1.07
    asted
    1.07
    anch
    1.06
    adders
    1.01
    ushing
    1.00
    Activations Density 0.017%

    No Known Activations