© 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. 0-RES-JB
    11. 19855
    Prev
    Next
    INDEX
    Explanations

    descriptions of positive attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to qualities and characteristics

    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
    bang
    -0.68
    ck
    -0.66
    mask
    -0.65
    acket
    -0.65
    lder
    -0.64
    EE
    -0.64
     targeted
    -0.63
    LL
    -0.61
     follow
    -0.60
    site
    -0.60
    POSITIVE LOGITS
     qualities
    3.50
     virtues
    2.17
     traits
    1.91
     attributes
    1.69
     strengths
    1.44
     sentiments
    1.41
     capacities
    1.36
     characteristics
    1.33
     talents
    1.33
     adject
    1.30
    Activations Density 0.012%

    No Known Activations