© 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. 17085
    Prev
    Next
    INDEX
    Explanations

    prefixes or suffixes attached to words

    oai_token-act-pair · gpt-3.5-turbo

    words related to importance or significance

    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
    izoph
    -0.67
     Frey
    -0.61
     LET
    -0.61
     residue
    -0.61
    paper
    -0.60
     Skydragon
    -0.60
    undy
    -0.60
     decom
    -0.59
     saline
    -0.57
     succ
    -0.56
    POSITIVE LOGITS
    achment
    0.83
    gyn
    0.79
    igious
    0.77
    olic
    0.73
    ãĥ¼ãĤ¯
    0.69
    kay
    0.68
    inka
    0.67
    asonic
    0.67
    ormon
    0.66
    akable
    0.66
    Activations Density 0.088%

    No Known Activations