© 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. 6-RES-JB
    11. 15001
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the speaker's level of knowledge or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing certainty or knowledge about a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī
    -0.71
     âĹı
    -0.69
    ++++
    -0.69
    oly
    -0.69
    omas
    -0.68
     Crimson
    -0.65
     Proc
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.62
     JO
    -0.60
     Gong
    -0.60
    POSITIVE LOGITS
     practicable
    0.73
    psc
    0.66
    tarians
    0.65
     feasible
    0.64
    lems
    0.64
    Minimum
    0.64
    earcher
    0.63
    Distance
    0.63
    outheast
    0.63
    plet
    0.62
    Activations Density 0.057%

    No Known Activations