© 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. 23505
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions of power or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "dictation" or "dictatorial" contexts

    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
    ned
    -0.71
     Shank
    -0.71
    WAYS
    -0.70
    Kin
    -0.69
    zee
    -0.67
    WARD
    -0.66
    iland
    -0.66
    Tur
    -0.65
    MER
    -0.64
    FIELD
    -0.64
    POSITIVE LOGITS
    orians
    1.06
    orian
    1.06
    atorial
    0.98
    ory
    0.97
    enance
    0.93
    ure
    0.91
     XVI
    0.88
    ict
    0.88
    orial
    0.88
    ine
    0.87
    Activations Density 0.035%

    No Known Activations