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

    Neuronpedia

    Jacobian LensNEW
    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. 2330
    Prev
    Next
    INDEX
    Explanations

    interesting, strange, or unusual occurrences or facts

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe novelty or curiosity

    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
    hops
    -0.99
    hers
    -0.87
    ULTS
    -0.83
    ernels
    -0.82
    ecause
    -0.79
    iants
    -0.79
     Tanks
    -0.78
    Ĥİ
    -0.78
    lees
    -0.78
    stones
    -0.78
    POSITIVE LOGITS
     twist
    1.14
     distinction
    1.09
     anecdote
    1.04
     tale
    1.02
     combination
    1.01
     example
    1.01
     caveat
    1.00
     array
    0.99
     statistic
    0.99
     glimpse
    0.99
    Activations Density 0.225%

    No Known Activations