© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12700
    Prev
    Next
    INDEX
    Explanations

    phrases indicating guidance or instruction

    oai_token-act-pair · gpt-3.5-turbo

    requests and directives for action or compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )—
    -0.84
    "—
    -0.81
     Rodham
    -0.77
    ËĪ
    -0.72
    SAN
    -0.71
    \.
    -0.71
    —"
    -0.69
     slam
    -0.66
    AFP
    -0.66
    ickle
    -0.65
    POSITIVE LOGITS
    Additionally
    0.92
     furthermore
    0.88
    Example
    0.86
     Additionally
    0.85
     additionally
    0.85
     Example
    0.85
     drawback
    0.84
     Examples
    0.83
    cknowled
    0.81
     exceptions
    0.81
    Activations Density 0.455%

    No Known Activations