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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4368
    Prev
    Next
    INDEX
    Explanations

    verbs related to cognitive processes, such as thinking and assessing

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate perception or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Applic
    -0.85
    FTWARE
    -0.73
     Apart
    -0.67
     streng
    -0.67
    foundland
    -0.65
     Palestin
    -0.65
     Applic
    -0.65
    iscons
    -0.63
     reluct
    -0.62
     CLR
    -0.62
    POSITIVE LOGITS
     ourselves
    0.67
    birds
    0.66
     yourselves
    0.65
    jit
    0.65
    arest
    0.65
    tec
    0.64
    poke
    0.63
    ings
    0.61
     caucuses
    0.60
    ida
    0.59
    Activations Density 0.464%

    No Known Activations