© 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. 12538
    Prev
    Next
    INDEX
    Explanations

    potential outcomes or consequences of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential outcomes or consequences

    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
     uniform
    -0.71
    ilty
    -0.64
    ele
    -0.62
    SPONSORED
    -0.59
     dances
    -0.59
     Dragonbound
    -0.59
    hyde
    -0.59
    rib
    -0.58
     invariably
    -0.58
     seldom
    -0.57
    POSITIVE LOGITS
    ħĭ
    1.05
     feas
    0.84
    ivably
    0.78
    olla
    0.75
    loo
    0.74
    »Ĵ
    0.73
    ãĥ¤
    0.73
     someday
    0.71
     mistaken
    0.71
    ruce
    0.69
    Activations Density 0.199%

    No Known Activations