© 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. 24045
    Prev
    Next
    INDEX
    Explanations

    terms related to physical posture and inclinations

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "lean."

    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
    ubs
    -0.81
    ridges
    -0.78
    cel
    -0.76
    uber
    -0.74
    ilet
    -0.73
    ãĥ£
    -0.73
    plain
    -0.72
    changed
    -0.71
    ilage
    -0.69
    protected
    -0.67
    POSITIVE LOGITS
     toward
    1.15
     towards
    1.09
     forward
    0.91
     heavily
    0.91
     heaviest
    0.90
     shoulders
    0.88
     lean
    0.83
     Towards
    0.81
     inward
    0.80
    onite
    0.79
    Activations Density 0.039%

    No Known Activations