© 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. 3-RES-JB
    11. 12177
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "cust" or related words like "custard."

    oai_token-act-pair · gpt-3.5-turbo

    terminologies related to computer programming and software services

    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
    swick
    -0.83
    stood
    -0.83
    erous
    -0.75
     Wildcats
    -0.73
    lift
    -0.70
    laws
    -0.70
     Appalachian
    -0.69
     flyer
    -0.67
    stand
    -0.66
     Advent
    -0.66
    POSITIVE LOGITS
    api
    1.14
    oca
    1.07
    istry
    0.92
    hod
    0.90
    utics
    0.89
    opoulos
    0.86
    á¸
    0.86
    rament
    0.82
    utor
    0.82
    utic
    0.81
    Activations Density 0.012%

    No Known Activations