© 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. 17064
    Prev
    Next
    INDEX
    Explanations

    names of locations or nationalities

    oai_token-act-pair · gpt-3.5-turbo

    references to national or regional identities and political affiliations

    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
    urtles
    -0.76
    uador
    -0.76
    hovah
    -0.74
    FontSize
    -0.72
    soType
    -0.70
    nell
    -0.69
     Canaver
    -0.69
    essler
    -0.68
    aples
    -0.67
    ]'
    -0.67
    POSITIVE LOGITS
     counterparts
    1.81
     counterpart
    1.72
     brethren
    1.41
     colleagues
    1.31
     cousins
    1.29
     colleague
    1.28
     namesake
    1.27
     predecessors
    1.22
     cousin
    1.21
     peers
    1.21
    Activations Density 0.469%

    No Known Activations