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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23431
    Prev
    Next
    INDEX
    Explanations

    keywords related to recruitment, such as "recruit," "employees," "students," and "volunteers."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recruitment, hiring, and employment demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknow
    -0.72
     degradation
    -0.65
    ©¶æ
    -0.64
    SourceFile
    -0.62
    ij士
    -0.59
     Nun
    -0.57
    saf
    -0.57
     Silence
    -0.57
     censorship
    -0.55
    gebra
    -0.54
    POSITIVE LOGITS
    hips
    1.37
    hip
    1.36
     whom
    1.23
     who
    1.15
     willing
    1.04
    who
    1.02
     into
    0.90
     interested
    0.83
     whose
    0.83
    ervatives
    0.83
    Activations Density 0.294%

    No Known Activations