© 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. 3-RES-JB
    11. 10720
    Prev
    Next
    INDEX
    Explanations

    words related to interactions with an audience or readers

    oai_token-act-pair · gpt-3.5-turbo

    references to an audience or viewers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erald
    -0.74
     Ide
    -0.73
    phrine
    -0.67
    empt
    -0.66
     Agric
    -0.63
     Franch
    -0.63
     Plum
    -0.62
    grave
    -0.61
    akeru
    -0.60
    icum
    -0.60
    POSITIVE LOGITS
     audience
    1.00
     audiences
    0.89
    atics
    0.86
     tuning
    0.84
    Reviewer
    0.82
    atically
    0.80
    ÃįÃį
    0.79
    room
    0.76
    members
    0.75
     tuned
    0.72
    Activations Density 0.017%

    No Known Activations