© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    proper names, possibly related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns referring to individuals, particularly those named Stephan and Horton

    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
     mathemat
    -0.88
     confir
    -0.83
     livest
    -0.81
     territ
    -0.81
    ccording
    -0.78
     destro
    -0.78
     princ
    -0.77
     nep
    -0.76
    rame
    -0.75
     veter
    -0.74
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.85
    abeth
    0.84
    iere
    0.81
    200000
    0.79
    istics
    0.79
    istic
    0.78
    ãĤ´ãĥ³
    0.78
    izophren
    0.77
    istical
    0.77
    geist
    0.76
    Activations Density 0.020%

    No Known Activations