© 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. 9-RES-JB
    11. 15408
    Prev
    Next
    INDEX
    Explanations

    words related to price

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pricing and security concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entimes
    -0.69
    ategor
    -0.69
    sbm
    -0.65
    enegger
    -0.63
    azeera
    -0.61
    agog
    -0.61
    PROV
    -0.59
    orio
    -0.59
    Cola
    -0.59
    hap
    -0.58
    POSITIVE LOGITS
     itself
    1.03
     of
    0.97
     thereof
    0.94
     discrepancy
    0.86
     portion
    0.84
     quo
    0.83
    liest
    0.80
     reversal
    0.76
     aspect
    0.75
     mismatch
    0.72
    Activations Density 0.526%

    No Known Activations