© 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. 4-RES-JB
    11. 24106
    Prev
    Next
    INDEX
    Explanations

    phrases related to trying or attempting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of quantifiers and methods related to trying or testing something

    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
     Mour
    -0.73
    threat
    -0.70
    said
    -0.68
    Introduced
    -0.68
     Frie
    -0.68
    """
    -0.63
     Species
    -0.62
    letters
    -0.61
     Languages
    -0.61
     Places
    -0.61
    POSITIVE LOGITS
    unal
    0.82
     unsuccessfully
    0.77
    emis
    0.75
     harder
    0.70
     emulate
    0.70
    alion
    0.70
     luck
    0.70
     sqor
    0.69
    wagen
    0.69
     hardest
    0.68
    Activations Density 0.152%

    No Known Activations