© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3529
    Prev
    Next
    INDEX
    Explanations

    proper nouns or aliases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "aka" used to refer to alternate names or identities

    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
    ttle
    -0.85
     ancest
    -0.71
    ĻĤ
    -0.68
     divisions
    -0.67
     inspectors
    -0.67
    iners
    -0.67
    iferation
    -0.66
    ticket
    -0.66
     positives
    -0.63
    encers
    -0.63
    POSITIVE LOGITS
    aka
    1.34
    unta
    0.99
    apo
    0.91
    isoft
    0.89
    ichi
    0.89
    oka
    0.86
    heim
    0.85
    ansas
    0.85
    awa
    0.84
    izu
    0.84
    Activations Density 0.006%

    No Known Activations