© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4800
    Prev
    Next
    INDEX
    Explanations

    similarities or comparisons between different groups of people, especially regarding financial or medical aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with specific personal attributes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onement
    -0.63
    ecause
    -0.63
    orpor
    -0.58
    oner
    -0.55
     Authors
    -0.54
     Relax
    -0.54
     relieved
    -0.54
     fray
    -0.54
    once
    -0.53
     hikers
    -0.53
    POSITIVE LOGITS
     disabilities
    1.10
     backgrounds
    1.04
     penchant
    1.03
     propensity
    0.99
     knack
    0.98
     vested
    0.91
     aspirations
    0.88
     histories
    0.87
     qualifications
    0.86
     predis
    0.85
    Activations Density 0.375%

    No Known Activations