© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 1629
    Prev
    Next
    INDEX
    Explanations

    keywords associated with different viewpoints or interpretations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'perspective' and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    codes
    -0.63
    Miss
    -0.63
     Hail
    -0.62
    riers
    -0.62
    exempt
    -0.60
    HM
    -0.60
    rupt
    -0.60
    letters
    -0.60
    Delivery
    -0.59
    Clean
    -0.59
    POSITIVE LOGITS
     perspective
    3.89
     perspectives
    2.69
     Perspective
    2.63
     standpoint
    2.59
     viewpoint
    2.54
     vantage
    2.13
     POV
    1.90
     perspect
    1.86
     viewpoints
    1.71
     context
    1.64
    Activations Density 0.017%

    No Known Activations