© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 4938
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to preparation or action

    oai_token-act-pair · gpt-3.5-turbo

    transitions and preparatory language related to beginning processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.84
    é¾
    -0.71
    path
    -0.66
    far
    -0.65
    cel
    -0.64
    ãĥĩ
    -0.64
     inconsistency
    -0.62
    bryce
    -0.61
     Occupations
    -0.58
    euro
    -0.57
    POSITIVE LOGITS
    avascript
    0.74
     suffice
    0.74
    ookie
    0.73
    acly
    0.72
    LET
    0.70
     Amin
    0.68
    inka
    0.67
    udence
    0.67
    apo
    0.67
     introdu
    0.66
    Activations Density 0.089%

    No Known Activations