© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 24066
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mans" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the term "Mans" and its variations, indicating a focus on a specific name or subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tical
    -0.73
    ENCY
    -0.71
     ED
    -0.70
    ties
    -0.69
    BOOK
    -0.67
    é¾įåĸļ士
    -0.67
    ļéĨĴ
    -0.65
    tics
    -0.64
    èª
    -0.64
    HER
    -0.64
    POSITIVE LOGITS
    laughter
    1.21
     Mans
    1.15
    pread
    0.97
    plain
    0.95
    amel
    0.93
    allah
    0.86
    hap
    0.85
     mans
    0.84
    achus
    0.83
    mans
    0.83
    Activations Density 0.006%

    No Known Activations