© 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. 5092
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assumptions or deductions being made about a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the notion of necessity or obligation

    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
    gewater
    -0.80
    opian
    -0.77
    emies
    -0.75
    adesh
    -0.65
    ocre
    -0.65
    oneliness
    -0.65
    aroo
    -0.65
     futures
    -0.62
    otion
    -0.61
    aband
    -0.61
    POSITIVE LOGITS
     deducted
    0.74
    :,
    0.74
    ENGTH
    0.70
    tein
    0.69
     acknow
    0.67
    NB
    0.67
     FANTASY
    0.65
    Authent
    0.63
    Acknowled
    0.63
    minimum
    0.62
    Activations Density 0.080%

    No Known Activations