© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    people, places, or organizations being highlighted for their excellence or significance

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "one of" followed by noteworthy entities or individuals

    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
    inity
    -0.63
     warranties
    -0.62
    udeau
    -0.61
    hips
    -0.60
     skins
    -0.60
     galleries
    -0.60
    lations
    -0.59
    ãĤµ
    -0.58
    cases
    -0.58
     detach
    -0.58
    POSITIVE LOGITS
     Hundred
    0.83
     hundred
    0.81
     dimensional
    0.77
    esan
    0.76
    rency
    0.74
     thing
    0.72
    handedly
    0.69
     sided
    0.68
    eenth
    0.68
     crore
    0.67
    Activations Density 0.089%

    No Known Activations