© 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. 2-RES-JB
    11. 23487
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of "peat" and its ecological implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word 'peat' and variations of the word

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.84
    schild
    -0.79
    oldemort
    -0.70
    pread
    -0.66
    swer
    -0.64
    traditional
    -0.64
    ãĤ¨ãĥ«
    -0.64
     guiActiveUnfocused
    -0.64
    hirt
    -0.63
     Parables
    -0.63
    POSITIVE LOGITS
    ggy
    0.86
    eper
    0.85
    eps
    0.84
    pperc
    0.82
    ptic
    0.81
    asant
    0.81
    pe
    0.79
    ared
    0.79
    leted
    0.78
    aking
    0.78
    Activations Density 0.008%

    No Known Activations