© 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. 3029
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases related to qualities and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    features describing the qualities or characteristics of things

    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
    ESE
    -0.82
     Levels
    -0.74
    vidia
    -0.72
    obos
    -0.72
    tera
    -0.71
    asio
    -0.70
    onds
    -0.70
    ._
    -0.69
    asma
    -0.68
    okia
    -0.67
    POSITIVE LOGITS
     unstoppable
    0.88
    etc
    0.86
     unheard
    0.84
    whatever
    0.83
     downright
    0.82
     exhilar
    0.77
     comprom
    0.76
     vind
    0.76
     unimagin
    0.76
     utterly
    0.75
    Activations Density 0.147%

    No Known Activations