© 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. 14697
    Prev
    Next
    INDEX
    Explanations

    names of locations or geography

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names related to locations and individuals

    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
    ICAN
    -0.77
     CPC
    -0.71
    Ĥª
    -0.64
    perture
    -0.63
    gdala
    -0.62
    vice
    -0.62
    alty
    -0.60
     PAX
    -0.60
     Booth
    -0.60
     mishand
    -0.59
    POSITIVE LOGITS
    keye
    0.96
    keyes
    0.87
    acebook
    0.84
     Grac
    0.83
    roots
    0.79
    nen
    0.78
    bent
    0.78
    minster
    0.77
    liga
    0.77
    jah
    0.75
    Activations Density 0.022%

    No Known Activations