© 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. 2-RES-JB
    11. 17725
    Prev
    Next
    INDEX
    Explanations

    references to the Gaza Strip

    oai_token-act-pair · gpt-3.5-turbo

    references to the Gaza Strip and related geopolitical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.92
    cipled
    -0.86
    fig
    -0.85
    MW
    -0.72
    Hug
    -0.72
    itating
    -0.70
    jay
    -0.67
    TABLE
    -0.67
    »Ĵ
    -0.66
    ML
    -0.66
    POSITIVE LOGITS
    istan
    0.76
     Cheong
    0.73
    eers
    0.73
    qa
    0.72
     Territories
    0.71
     Bulgaria
    0.69
     Lebanon
    0.68
     overrun
    0.66
     Juda
    0.66
     extrad
    0.65
    Activations Density 0.098%

    No Known Activations