Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15697
    Prev
    Next
    INDEX
    Explanations

    phrases related to directions (left or right) or layout (eg. "left hand side")

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to creation and directionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anut
    -0.72
    trap
    -0.71
     Flavoring
    -0.70
    exempt
    -0.70
    prep
    -0.69
    GW
    -0.69
    iasco
    -0.66
    estic
    -0.66
    imum
    -0.65
    ERN
    -0.64
    POSITIVE LOGITS
     flank
    0.82
     axis
    0.77
    hander
    0.75
     latitude
    0.70
     navigation
    0.70
     arrow
    0.70
     Arrow
    0.67
     aperture
    0.66
     arrows
    0.66
     citizenship
    0.65
    Activations Density 0.170%

    No Known Activations