© 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. 9-RES-JB
    11. 15396
    Prev
    Next
    INDEX
    Explanations

    adjectives describing enjoyment or desirability

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to"

    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
    afety
    -0.75
    calling
    -0.72
    hent
    -0.71
    arity
    -0.71
    vich
    -0.70
    urances
    -0.66
    uli
    -0.62
    urance
    -0.62
    eon
    -0.61
    hur
    -0.59
    POSITIVE LOGITS
     behold
    1.32
     contemplate
    1.21
     begin
    1.03
     navigate
    1.00
     contend
    0.96
    ggles
    0.95
     undertake
    0.93
     pursue
    0.92
     administer
    0.92
     acquire
    0.91
    Activations Density 0.157%

    No Known Activations