© 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. 4038
    Prev
    Next
    INDEX
    Explanations

    unrelated phrases and names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Pl" typically referring to "Plaza."

    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
     Jama
    -0.84
     curfew
    -0.83
    dar
    -0.78
     embargo
    -0.76
     offence
    -0.75
     Dal
    -0.74
     lash
    -0.74
     intro
    -0.73
     offense
    -0.71
     gang
    -0.69
    POSITIVE LOGITS
    Pl
    3.60
     Pl
    1.89
    pl
    1.68
    PL
    1.50
    Plan
    1.48
     Plat
    1.37
     PL
    1.28
    Pot
    1.26
     pl
    1.24
    plates
    1.23
    Activations Density 0.011%

    No Known Activations