© 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. 7-RES-JB
    11. 19530
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity named "Ha" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "Haaretz" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eenth
    -0.87
    âķIJ
    -0.84
    icipated
    -0.80
    eers
    -0.79
    manship
    -0.76
    ments
    -0.76
    mented
    -0.74
    hips
    -0.73
    ij士
    -0.72
     Alchemist
    -0.68
    POSITIVE LOGITS
    irst
    1.11
    vel
    1.09
    Ha
    0.97
    pless
    0.96
    ifa
    0.96
    iku
    0.92
    iley
    0.92
    aretz
    0.92
    verty
    0.90
    ugh
    0.89
    Activations Density 0.009%

    No Known Activations