© 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. 6-RES-JB
    11. 15061
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives for products or objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating high quality and positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etus
    -0.77
     chromosomes
    -0.72
     Intellectual
    -0.68
     credits
    -0.67
    lling
    -0.67
    birth
    -0.64
     transcripts
    -0.64
     Negro
    -0.63
    reys
    -0.62
    stan
    -0.62
    POSITIVE LOGITS
    anmar
    0.89
    theless
    0.84
     customizable
    0.80
     versatility
    0.79
     versatile
    0.79
     erg
    0.78
     outdoors
    0.78
     customization
    0.76
     UD
    0.75
     usability
    0.74
    Activations Density 0.261%

    No Known Activations