© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 18025
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating an alternative name or title for subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eways
    -0.74
    assian
    -0.68
    vantage
    -0.67
    legraph
    -0.67
    iotic
    -0.67
    ihara
    -0.66
    othal
    -0.65
    eff
    -0.64
    eway
    -0.63
    benefit
    -0.61
    POSITIVE LOGITS
     nicknamed
    1.05
     known
    1.01
     renamed
    0.89
     dubbed
    0.87
     spelled
    0.86
     referred
    0.84
     abbre
    0.77
     marketed
    0.76
    known
    0.76
     styled
    0.76
    Activations Density 0.106%

    No Known Activations