© 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. 10-RES-JB
    11. 12160
    Prev
    Next
    INDEX
    Explanations

    organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alam
    -0.71
    Ô
    -0.71
    +.
    -0.67
    âĢ¢âĢ¢
    -0.65
    ãĤĵ
    -0.64
    ++++
    -0.63
    ¢
    -0.62
    ||||
    -0.62
    agascar
    -0.62
    ween
    -0.62
    POSITIVE LOGITS
     intends
    1.15
     expects
    1.08
     chose
    1.08
     opted
    1.06
     believes
    1.00
     considers
    0.99
     undertook
    0.98
     maintains
    0.98
     operates
    0.97
     strives
    0.97
    Activations Density 0.257%

    No Known Activations