© 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. 7350
    Prev
    Next
    INDEX
    Explanations

    links or locations indicated by the word "here."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "here."

    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
    iven
    -0.67
    Zen
    -0.63
    visors
    -0.61
    ively
    -0.61
    iliary
    -0.61
    amac
    -0.58
    Sense
    -0.56
    uality
    -0.56
     funer
    -0.56
    ework
    -0.56
    POSITIVE LOGITS
    tical
    1.17
    tics
    1.08
    tic
    1.01
    abouts
    0.96
    here
    0.76
     guiActiveUn
    0.71
     newsp
    0.71
     âĨij
    0.69
    ford
    0.65
    zn
    0.65
    Activations Density 0.044%

    No Known Activations