© 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. 4-RES-JB
    11. 12260
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and commands

    oai_token-act-pair · gpt-3.5-turbo

    local installation commands and related technical instructions

    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
     âĢº
    -0.59
    ãĥķãĤ©
    -0.51
    ãĥ£
    -0.50
    ãĥ©ãĥ³
    -0.48
     Ag
    -0.47
    ...
    -0.46
    ,...
    -0.46
    Enlarge
    -0.45
    weed
    -0.45
    Fast
    -0.43
    POSITIVE LOGITS
     rul
    0.69
    endif
    0.67
     condem
    0.67
     destro
    0.63
    ahime
    0.58
    anwhile
    0.58
    hovah
    0.57
    utenberg
    0.56
    uliffe
    0.56
    )=(
    0.53
    Activations Density 2.900%

    No Known Activations