© 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. 23971
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or political events related to Balochistan

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and names, particularly related to geopolitical contexts

    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
     newsletters
    -0.78
    FORMATION
    -0.75
     refere
    -0.70
    FTWARE
    -0.68
    }}}
    -0.68
    £ı
    -0.68
     fermented
    -0.64
     pse
    -0.62
    MAP
    -0.61
    iddles
    -0.61
    POSITIVE LOGITS
    dash
    0.84
    istan
    0.80
    adesh
    0.76
    bia
    0.71
    ette
    0.69
    ieri
    0.67
    atti
    0.65
    anova
    0.64
    obin
    0.64
    eros
    0.63
    Activations Density 0.115%

    No Known Activations