© 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. 2816
    Prev
    Next
    INDEX
    Explanations

    instructions related to specific actions or tasks followed by a statement of purpose or result

    oai_token-act-pair · gpt-3.5-turbo

    causal phrases and instructions related to actions or processes

    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
    polit
    -0.84
    Financial
    -0.79
    orthy
    -0.78
    Liberal
    -0.76
    Online
    -0.72
    efe
    -0.72
     publicly
    -0.71
     politic
    -0.71
    Public
    -0.69
    Community
    -0.69
    POSITIVE LOGITS
     vibrations
    1.10
     it
    1.00
     your
    0.97
     airflow
    0.94
     you
    0.93
     moisture
    0.91
     gravity
    0.91
     photons
    0.90
     streaks
    0.90
     flakes
    0.89
    Activations Density 0.427%

    No Known Activations