© 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. 6656
    Prev
    Next
    INDEX
    Explanations

    the word "answer" appearing in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "answer" in varying contexts

    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
    wana
    -0.85
    erker
    -0.73
    ovie
    -0.71
    awar
    -0.69
    ammy
    -0.68
    arnaev
    -0.66
    akin
    -0.65
    ony
    -0.65
    robat
    -0.65
    chin
    -0.64
    POSITIVE LOGITS
    ysis
    1.08
     answ
    1.03
    answer
    0.98
     answer
    0.96
    swers
    0.89
     [+]
    0.87
     answered
    0.86
    Answer
    0.85
     answering
    0.81
     Answer
    0.81
    Activations Density 0.016%

    No Known Activations