© 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. 4-RES-JB
    11. 8485
    Prev
    Next
    INDEX
    Explanations

    specific instances or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one" followed by various contextual elements, indicating singular instances or reports within a narrative

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

    No Comments

    Negative Logits
     Recomm
    -0.69
    orum
    -0.65
     Janeiro
    -0.65
     \'
    -0.64
    atform
    -0.64
    bara
    -0.63
    inic
    -0.63
    fps
    -0.63
    ivist
    -0.62
    mire
    -0.62
    POSITIVE LOGITS
    DragonMagazine
    0.62
     maternal
    0.62
     verbs
    0.61
     modifiers
    0.61
    rav
    0.61
     topical
    0.61
     signature
    0.60
     spoken
    0.59
     remnants
    0.59
     aforementioned
    0.59
    Activations Density 0.446%

    No Known Activations