© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    titles or references to episodes in a series

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ep" along with its variations and related content

    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
    FUL
    -0.68
     unauthorized
    -0.67
     latitude
    -0.63
    hips
    -0.62
     clearance
    -0.62
     Opposition
    -0.60
     AMERICA
    -0.59
     unusual
    -0.59
    LESS
    -0.57
     eventual
    -0.57
    POSITIVE LOGITS
    hemer
    1.67
    iphany
    1.64
    isodes
    1.53
    iscopal
    1.48
    istle
    1.26
    onymous
    1.20
    igraph
    1.19
    idem
    1.11
    iph
    1.11
    oxy
    1.08
    Activations Density 0.029%

    No Known Activations