© 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. 13838
    Prev
    Next
    INDEX
    Explanations

    reference to a specific location within a text

    oai_token-act-pair · gpt-3.5-turbo

    the word "here" in various contexts

    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
     judgement
    -0.63
    visors
    -0.61
    cers
    -0.59
    IENT
    -0.58
     elimination
    -0.58
    amines
    -0.58
     consequence
    -0.57
     havoc
    -0.57
    iven
    -0.57
     concentration
    -0.56
    POSITIVE LOGITS
    tical
    1.32
    tics
    1.27
    abouts
    1.27
    tic
    1.07
    with
    0.77
    ford
    0.71
    endix
    0.70
     https
    0.70
    after
    0.69
     http
    0.69
    Activations Density 0.038%

    No Known Activations