© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 22573
    Prev
    Next
    INDEX
    Explanations

    questions, doubts, interests, and preferences expressed in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing doubt or invitation for communication

    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
    Els
    -0.87
    ãĥ³ãĤ¸
    -0.75
    Rod
    -0.73
    ãĥķ
    -0.71
    Ts
    -0.67
    "},
    -0.66
    mobi
    -0.66
    Coun
    -0.63
    ãĤ¤ãĥĪ
    -0.62
    roxy
    -0.61
    POSITIVE LOGITS
     succeed
    0.76
    pires
    0.72
     correctly
    0.72
     sufficiently
    0.71
     DEBUG
    0.71
     properly
    0.70
     incorrectly
    0.67
     remotely
    0.66
    rha
    0.65
    tains
    0.65
    Activations Density 0.613%

    No Known Activations