© 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. 7-RES-JB
    11. 17166
    Prev
    Next
    INDEX
    Explanations

    information related to particular events, organizations, or people

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or sentence boundaries

    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
     plunge
    -0.73
     doub
    -0.64
     cut
    -0.64
     hypot
    -0.64
     trusted
    -0.62
     desired
    -0.62
    ophob
    -0.61
     citiz
    -0.60
     deval
    -0.60
     habit
    -0.60
    POSITIVE LOGITS
    These
    1.13
    Together
    1.12
    Each
    1.08
    Among
    1.06
    Their
    1.05
    Tickets
    1.04
    Contribut
    0.99
    Those
    0.99
    They
    0.98
    Both
    0.97
    Activations Density 0.682%

    No Known Activations