© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 497
    Prev
    Next
    INDEX
    Explanations

    instances where the word "to" is followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "get to" in various contexts

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

    No Comments

    Negative Logits
     Measures
    -0.68
     deserves
    -0.60
     preceded
    -0.60
     Beng
    -0.59
     apartheid
    -0.58
     looms
    -0.58
     Rahman
    -0.58
    Statement
    -0.57
    abiding
    -0.56
    frames
    -0.56
    POSITIVE LOGITS
     grips
    0.92
    asted
    0.92
    asty
    0.83
    wered
    0.77
    ggles
    0.76
     settle
    0.75
     congratulate
    0.75
    pload
    0.73
     fulfill
    0.72
    axy
    0.72
    Activations Density 0.079%

    No Known Activations