© 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. 1728
    Prev
    Next
    INDEX
    Explanations

    adjectives denoting strong characteristics or actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "bold" and its variations

    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
     Cheong
    -0.95
    OTOS
    -0.87
    UTERS
    -0.71
    yer
    -0.65
    ADS
    -0.64
    ersion
    -0.64
    UT
    -0.64
    rera
    -0.64
    enfranch
    -0.62
    rogens
    -0.62
    POSITIVE LOGITS
    bold
    1.09
     bold
    0.99
    faced
    0.96
    face
    0.95
     Ital
    0.90
    er
    0.88
    ness
    0.87
    itude
    0.82
    olini
    0.79
     ital
    0.74
    Activations Density 0.012%

    No Known Activations