© 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. 22758
    Prev
    Next
    INDEX
    Explanations

    words related to prediction or importance

    oai_token-act-pair · gpt-3.5-turbo

    words related to authority or leadership roles

    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
     Brawl
    -0.81
     Mobility
    -0.76
     Adventure
    -0.63
    ooter
    -0.63
    ifled
    -0.63
     KB
    -0.62
    ooters
    -0.62
    athlon
    -0.62
    TAG
    -0.62
    ooting
    -0.62
    POSITIVE LOGITS
     pres
    4.02
    Pres
    1.61
     Pres
    1.51
    pres
    1.44
     PRES
    1.19
     presiding
    1.16
     prem
    1.14
     presided
    1.12
    PRES
    1.11
     prophetic
    1.08
    Activations Density 0.018%

    No Known Activations