© 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. 19656
    Prev
    Next
    INDEX
    Explanations

    clauses starting with "For the" and ending with particular phrases or themes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey the concept of "the most part" or generalizations about various topics

    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
     limb
    -0.64
     stuffing
    -0.61
    oshenko
    -0.60
    Sax
    -0.60
    Pad
    -0.59
     Notting
    -0.58
    osterone
    -0.57
     positively
    -0.57
    ãģ®å
    -0.56
     mathemat
    -0.55
    POSITIVE LOGITS
     sake
    1.40
     purposes
    1.19
     reasons
    0.94
    icion
    0.91
    erity
    0.70
    ummies
    0.70
    ulz
    0.67
     refres
    0.67
    idents
    0.66
    gencies
    0.64
    Activations Density 0.208%

    No Known Activations