© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10093
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases indicating admiration or surprise

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express amazement or emphasis

    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
     Poe
    -0.74
     heroin
    -0.65
    mone
    -0.64
     Dickinson
    -0.63
     admitting
    -0.60
    gage
    -0.59
     choke
    -0.58
     poppy
    -0.57
    staking
    -0.57
    rency
    -0.56
    POSITIVE LOGITS
    ãĤ»
    0.79
    ?]
    0.79
    cott
    0.79
    azes
    0.78
    ?:
    0.75
    SPONSORED
    0.71
    natureconservancy
    0.71
    æĥ
    0.71
    bourg
    0.71
    abee
    0.70
    Activations Density 0.174%

    No Known Activations