© 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. 22569
    Prev
    Next
    INDEX
    Explanations

    phrases involving physical placement or positioning

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "onto" in various contexts

    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
    pport
    -0.70
    inus
    -0.66
    ub
    -0.61
     Cases
    -0.58
     difference
    -0.55
     reasons
    -0.54
    cel
    -0.54
    Percent
    -0.53
    orce
    -0.53
     regards
    -0.53
    POSITIVE LOGITS
     onto
    3.48
     into
    1.54
     INTO
    1.32
    onto
    1.29
     Into
    1.17
    into
    1.16
     overboard
    1.12
     atop
    1.02
     onward
    1.00
     onwards
    0.93
    Activations Density 0.021%

    No Known Activations