© 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. 2867
    Prev
    Next
    INDEX
    Explanations

    mentions of interviews and discussions related to media content

    oai_token-act-pair · gpt-3.5-turbo

    segments of conversation or discussion regarding filmmaking and interviews

    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
     wrongly
    -0.76
    vernment
    -0.74
    ":"/
    -0.73
     denies
    -0.73
    wagen
    -0.70
     Photograph
    -0.69
    ['
    -0.69
    iage
    -0.69
    jet
    -0.69
    gio
    -0.67
    POSITIVE LOGITS
    Episode
    1.07
    podcast
    1.03
     Episode
    1.00
     Podcast
    0.99
     LIVE
    0.99
    CAST
    0.92
     podcast
    0.89
    Guest
    0.88
    estern
    0.88
    âķIJ
    0.88
    Activations Density 0.473%

    No Known Activations