© 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. 19333
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a stage or process of development or implementation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate progression or stages in processes

    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
     Ago
    -0.84
    PLIED
    -0.65
    allow
    -0.63
     Skies
    -0.60
     Played
    -0.60
    stay
    -0.59
    cit
    -0.59
    hold
    -0.59
    =-=-=-=-=-=-=-=-
    -0.58
    lat
    -0.58
    POSITIVE LOGITS
     completing
    1.42
     acquiring
    1.40
     figuring
    1.29
     becoming
    1.27
     discovering
    1.26
     constructing
    1.26
     establishing
    1.24
     rebuilding
    1.23
     mastering
    1.23
     obtaining
    1.23
    Activations Density 0.187%

    No Known Activations