© 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. 8-RES-JB
    11. 20244
    Prev
    Next
    INDEX
    Explanations

    countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations and political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    requisite
    -0.60
    cause
    -0.60
    into
    -0.58
    planet
    -0.58
    },"
    -0.57
    him
    -0.56
    aciously
    -0.55
     invade
    -0.55
    orio
    -0.54
    -+
    -0.53
    POSITIVE LOGITS
     there
    0.99
     meanwhile
    0.91
     they
    0.88
     we
    0.83
    there
    0.75
     it
    0.73
     however
    0.72
     THERE
    0.70
     THEY
    0.67
    ,
    0.67
    Activations Density 0.372%

    No Known Activations