© 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. 4-RES-JB
    11. 13056
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of organizations that are led by someone

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "led by" in various contexts

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

    No Comments

    Negative Logits
    enery
    -0.75
    itta
    -0.74
    IDER
    -0.70
    blems
    -0.70
    Rate
    -0.69
     manif
    -0.68
    ased
    -0.67
    chanted
    -0.65
    WHERE
    -0.65
    uality
    -0.65
    POSITIVE LOGITS
     virtue
    0.89
    venture
    0.85
     reins
    0.74
     Ellen
    0.73
    illac
    0.72
    urion
    0.71
    laws
    0.71
     Ay
    0.69
    gone
    0.68
     Henry
    0.68
    Activations Density 0.069%

    No Known Activations