© 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. 10-RES-JB
    11. 12756
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preference or desirability

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating hypothetical or conditional situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.65
    ãĤ¨ãĥ«
    -0.63
    sometimes
    -0.61
    culosis
    -0.61
    rising
    -0.60
    iop
    -0.59
     Commando
    -0.57
    PsyNetMessage
    -0.57
    idem
    -0.56
     Kurd
    -0.56
    POSITIVE LOGITS
     unthinkable
    1.09
     preferable
    1.06
     impossible
    1.03
     impractical
    0.96
     prohib
    0.95
     folly
    0.93
     laughable
    0.93
     foolish
    0.92
     appreciated
    0.91
     nice
    0.91
    Activations Density 0.105%

    No Known Activations