© 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. 11-RES-JB
    11. 22491
    Prev
    Next
    INDEX
    Explanations

    data related to research studies and reports

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to survey results and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.71
     toast
    -0.69
    twitch
    -0.59
     filibuster
    -0.59
    emate
    -0.59
    CEPT
    -0.58
     Toast
    -0.57
    Origin
    -0.57
     wear
    -0.57
    DN
    -0.56
    POSITIVE LOGITS
     found
    1.49
     concluded
    1.39
     surveyed
    1.32
     showed
    1.31
     predicts
    1.28
     analyzed
    1.27
     estimated
    1.23
     concludes
    1.21
     examined
    1.21
     calculates
    1.20
    Activations Density 0.346%

    No Known Activations