© 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. 8-RES-JB
    6. 3048
    Prev
    Next
    INDEX
    Explanations

    entries related to programming functions and commands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "get" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deduct
    -0.61
     anecd
    -0.59
     Tower
    -0.58
     seals
    -0.57
     deliberations
    -0.57
     slurs
    -0.57
    orough
    -0.55
     exh
    -0.53
    velt
    -0.53
     Diary
    -0.53
    POSITIVE LOGITS
    TING
    1.23
     rid
    1.08
    cloneembedreportprint
    0.98
    tin
    0.92
    away
    0.91
    ãĥ³ãĤ¸
    0.89
    ter
    0.78
    aways
    0.77
    ters
    0.77
    zsche
    0.77
    Activations Density 0.046%

    No Known Activations