© 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. 4927
    Prev
    Next
    INDEX
    Explanations

    contractions with "'s."

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the contraction "it's" or similar expressions of sentiment about challenging or noteworthy situations

    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
    %%
    -0.73
    ESE
    -0.70
     LAT
    -0.68
     wield
    -0.68
    éĹĺ
    -0.67
    units
    -0.67
    vale
    -0.66
    ipient
    -0.64
    ievers
    -0.64
    successfully
    -0.63
    POSITIVE LOGITS
     unbelievable
    1.17
     gonna
    1.14
     bitters
    1.07
     raining
    1.06
     surreal
    1.04
     heartbreaking
    1.04
     funny
    1.04
     ironic
    1.03
     frustrating
    1.02
     definitely
    1.02
    Activations Density 0.238%

    No Known Activations