© 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. 22466
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluating or considering different options

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing interest or relevance to a selected topic

    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
     ALWAYS
    -0.76
    always
    -0.76
     relentlessly
    -0.72
     tirelessly
    -0.68
     invariably
    -0.68
    ĸļ
    -0.67
     meticulously
    -0.66
    shall
    -0.65
    ascus
    -0.65
    athan
    -0.65
    POSITIVE LOGITS
     someday
    1.26
     somew
    1.00
     some
    1.00
     reconsider
    0.91
     wiser
    0.87
     sooner
    0.86
     unintended
    0.83
     slightly
    0.83
     undesirable
    0.82
     recons
    0.81
    Activations Density 0.539%

    No Known Activations