© 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. 9-RES-JB
    11. 15727
    Prev
    Next
    INDEX
    Explanations

    information about individuals and their roles, actions, or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "also" and other related verbs or descriptors indicating inclusion or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     honestly
    -0.77
     ONLY
    -0.73
     NEVER
    -0.71
     whichever
    -0.69
     happiest
    -0.68
     nevertheless
    -0.66
    only
    -0.65
    whatever
    -0.65
     invariably
    -0.65
     actually
    -0.65
    POSITIVE LOGITS
    ypes
    0.89
    ebted
    0.75
     affected
    0.70
    racted
    0.67
    ilyn
    0.66
     confir
    0.65
    sie
    0.63
    rieved
    0.63
     GOODMAN
    0.63
     sidx
    0.63
    Activations Density 0.332%

    No Known Activations