© 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. 456
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a continuation or progression of a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuation or ongoing actions

    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
     Surprise
    -0.94
     Skin
    -0.75
     Yosemite
    -0.71
     Abdel
    -0.70
     Ha
    -0.69
     Mesa
    -0.68
     Runner
    -0.68
     Jaw
    -0.67
     Ans
    -0.66
     Wrap
    -0.65
    POSITIVE LOGITS
    tions
    0.89
    abre
    0.83
     adolesc
    0.82
    clusively
    0.80
    :]
    0.76
    nces
    0.75
    ussions
    0.73
    orks
    0.73
    azeera
    0.72
    rily
    0.72
    Activations Density 0.182%

    No Known Activations