© 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. 1-RES-JB
    11. 1047
    Prev
    Next
    INDEX
    Explanations

    terms related to spectrometry

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spect" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lishes
    -0.67
    thritis
    -0.66
    apsed
    -0.63
     discharged
    -0.63
    gb
    -0.62
    bably
    -0.61
    capacity
    -0.61
    BY
    -0.60
    ¶ħ
    -0.59
    gur
    -0.58
    POSITIVE LOGITS
     spect
    1.21
    rums
    1.13
    uous
    0.87
    acles
    0.82
    rosc
    0.79
    ively
    0.78
     Seym
    0.77
    Spect
    0.77
    icons
    0.76
    natureconservancy
    0.76
    Activations Density 0.009%

    No Known Activations