© 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. 2-RES-JB
    11. 13400
    Prev
    Next
    INDEX
    Explanations

    locations and venues

    oai_token-act-pair · gpt-3.5-turbo

    prepositions that indicate location or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     %%
    -0.73
     fortun
    -0.69
     incumb
    -0.68
     ingred
    -0.67
    /(
    -0.67
    username
    -0.67
     redund
    -0.66
     arrang
    -0.65
    untled
    -0.65
     includ
    -0.64
    POSITIVE LOGITS
     lieu
    1.14
     conjunction
    1.08
     accordance
    1.07
     vitro
    0.93
    clusions
    0.93
    clus
    0.91
     order
    0.89
     tandem
    0.88
     unison
    0.88
    patient
    0.86
    Activations Density 0.843%

    No Known Activations