© 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. 4087
    Prev
    Next
    INDEX
    Explanations

    informal, colloquial language including slang and casual speech patterns

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives that convey a sense of texture or quality

    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
    SEA
    -0.86
    ajor
    -0.84
    roit
    -0.71
    igate
    -0.71
    rait
    -0.70
    uther
    -0.67
    URA
    -0.67
    angan
    -0.66
    Ĥİ
    -0.65
    arium
    -0.65
    POSITIVE LOGITS
    ness
    0.99
     eyed
    0.96
     little
    0.95
    glers
    0.88
    nesses
    0.88
     old
    0.85
     sounding
    0.82
     beasts
    0.82
     bits
    0.81
     blob
    0.81
    Activations Density 0.112%

    No Known Activations