© 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. 419
    Prev
    Next
    INDEX
    Explanations

    mentions of radio shows and hosts

    oai_token-act-pair · gpt-3.5-turbo

    references to radio interview 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
    gradation
    -0.81
    origin
    -0.75
    property
    -0.74
    digy
    -0.73
    development
    -0.68
    export
    -0.67
     labou
    -0.66
    gra
    -0.66
    plementation
    -0.65
    ignty
    -0.65
    POSITIVE LOGITS
     interviewer
    1.14
     Hannity
    1.04
     interviews
    0.99
     briefings
    0.98
     interview
    0.98
     microphones
    0.96
     aired
    0.96
     CNBC
    0.91
     speeches
    0.90
     airing
    0.90
    Activations Density 0.279%

    No Known Activations