© 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. 9071
    Prev
    Next
    INDEX
    Explanations

    phrases related to standard or expected situations

    oai_token-act-pair · gpt-3.5-turbo

    references to routine or expected behaviors

    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
    zon
    -0.86
    vic
    -0.74
     Rica
    -0.73
    PAC
    -0.68
    arate
    -0.66
    ÄŁ
    -0.65
    ittees
    -0.64
    odan
    -0.64
    ï¸ı
    -0.63
    wic
    -0.63
    POSITIVE LOGITS
    osphere
    0.83
     tendency
    0.80
     thing
    0.77
    est
    0.75
     term
    0.75
     antidote
    0.75
     picture
    0.74
     populace
    0.73
     notion
    0.73
    cients
    0.71
    Activations Density 0.142%

    No Known Activations