© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4746
    Prev
    Next
    INDEX
    Explanations

    verbs, nouns, and adjectives related to sustenance and support

    oai_token-act-pair · gpt-3.5-turbo

    words related to sustenance and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andals
    -0.91
    Lock
    -0.75
     Inspector
    -0.71
    ricks
    -0.71
    ICS
    -0.70
     Rhodes
    -0.67
     inspector
    -0.67
    stown
    -0.65
    HO
    -0.65
    naire
    -0.64
    POSITIVE LOGITS
     sust
    2.69
     nour
    2.54
     succ
    1.43
     resp
    1.39
     replen
    1.35
     upl
    1.32
     feast
    1.31
     recomp
    1.22
     nurt
    1.21
     entr
    1.18
    Activations Density 0.071%

    No Known Activations