© 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. 3-RES-JB
    11. 15099
    Prev
    Next
    INDEX
    Explanations

    words related to satisfaction and approval

    oai_token-act-pair · gpt-3.5-turbo

    words related to satisfaction and acceptable evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umn
    -0.69
    olan
    -0.68
    artifacts
    -0.68
    pmwiki
    -0.66
     Torn
    -0.65
    fi
    -0.65
    enic
    -0.64
    planes
    -0.64
    plane
    -0.63
     shortened
    -0.63
    POSITIVE LOGITS
     Satisf
    1.16
     satisfied
    1.14
     satisfaction
    1.07
    atisf
    1.03
     satisfy
    0.98
    actory
    0.91
     satisfies
    0.91
     satisf
    0.87
    ysis
    0.87
    MENTS
    0.87
    Activations Density 0.017%

    No Known Activations