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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 4027
    Prev
    Next
    INDEX
    Explanations

    information related to directions and orientations

    oai_token-act-pair · gpt-3.5-turbo

    details related to positioning and orientation in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akings
    -0.71
     Flavoring
    -0.70
    onut
    -0.65
    Skin
    -0.64
    ufact
    -0.64
    ãĥ¯ãĥ³
    -0.63
     Bleach
    -0.63
    ologne
    -0.63
    ineries
    -0.61
    ritten
    -0.60
    POSITIVE LOGITS
     perpendicular
    1.19
     horizontally
    1.15
     perpend
    1.14
     angled
    1.07
     vertically
    1.05
     downwards
    0.95
     direction
    0.95
    wards
    0.94
     sideways
    0.94
     opposite
    0.93
    Activations Density 0.357%

    No Known Activations