© 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. 0-RES-JB
    11. 3757
    Prev
    Next
    INDEX
    Explanations

    verbs related to entanglement or tangling

    oai_token-act-pair · gpt-3.5-turbo

    words related to angles or angular shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lore
    -0.63
     rate
    -0.62
     discount
    -0.62
     Tim
    -0.62
     quiz
    -0.61
     (/
    -0.61
     vote
    -0.60
     Info
    -0.59
     Devin
    -0.59
     storm
    -0.58
    POSITIVE LOGITS
    angled
    4.50
    angling
    2.43
    angles
    2.23
    angler
    1.52
    angle
    1.30
    wered
    0.99
    ucked
    0.99
     dangling
    0.96
    DonaldTrump
    0.92
    isted
    0.92
    Activations Density 0.032%

    No Known Activations