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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17787
    Prev
    Next
    INDEX
    Explanations

    names of people, companies, and positions

    oai_token-act-pair · gpt-3.5-turbo

    names of organizations, teams, or notable entities

    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
     Retrieved
    -0.66
     });
    -0.64
    ?).
    -0.63
    ··
    -0.63
     disapp
    -0.60
     outweigh
    -0.60
    }}}
    -0.59
    perse
    -0.59
     $$
    -0.57
     Poles
    -0.57
    POSITIVE LOGITS
     fray
    0.66
    ecause
    0.58
    agar
    0.57
     Lloyd
    0.56
     Premier
    0.55
     Colleg
    0.55
     Genetics
    0.55
    bank
    0.54
    oreal
    0.54
    dale
    0.53
    Activations Density 0.857%

    No Known Activations