© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability

    oai_token-act-pair · gpt-3.5-turbo

    patterns of punctuation and non-verbal expressions

    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
    mith
    -0.72
    ppelin
    -0.68
    ori
    -0.67
    azi
    -0.67
    ogle
    -0.62
    xes
    -0.61
    enei
    -0.61
    yles
    -0.61
    ãĥīãĥ©
    -0.60
    ogly
    -0.60
    POSITIVE LOGITS
     ."
    1.48
     ,"
    1.16
     .)
    1.04
     .
    1.02
    until
    0.88
    shall
    0.84
     Hmm
    0.82
    ↵Âł
    0.82
     ]
    0.80
     Nope
    0.80
    Activations Density 0.019%

    No Known Activations