© 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. 2-RES-JB
    11. 24026
    Prev
    Next
    INDEX
    Explanations

    terms related to programming or technology, particularly those starting with 'am'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "am."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tang
    -0.73
     Durham
    -0.69
    theless
    -0.65
     externalToEVAOnly
    -0.64
     Titanic
    -0.63
     kinderg
    -0.63
     Crus
    -0.63
    culosis
    -0.62
    ãģį
    -0.62
     learners
    -0.61
    POSITIVE LOGITS
    sterdam
    1.25
    azon
    1.19
    ethyst
    1.07
    essage
    0.99
    icus
    0.99
    ateurs
    0.99
    ajor
    0.95
    nesty
    0.94
    endment
    0.93
    azes
    0.93
    Activations Density 0.023%

    No Known Activations