© 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. 0-RES-JB
    11. 23102
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person named Hal

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cc
    -0.72
     spider
    -0.68
    vez
    -0.67
    CV
    -0.66
    ansas
    -0.65
    */(
    -0.65
    »Ĵ
    -0.64
     bully
    -0.64
     bullied
    -0.63
    VM
    -0.63
    POSITIVE LOGITS
     Hal
    3.77
    Hal
    3.08
     hal
    2.15
    hal
    1.73
     HAL
    1.49
     Hau
    1.16
     Tal
    1.13
     Gil
    1.12
     Khal
    1.09
     Shal
    1.08
    Activations Density 0.019%

    No Known Activations