© 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. 9479
    Prev
    Next
    INDEX
    Explanations

    references to a specific sports team named "Ravens"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Raven" or "Ravens" in various contexts

    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
    awaru
    -0.90
    olulu
    -0.79
    olate
    -0.77
    ype
    -0.75
    rists
    -0.73
    yip
    -0.72
     Nicaragua
    -0.70
    Ĵ
    -0.70
    buquerque
    -0.70
    ichita
    -0.68
    POSITIVE LOGITS
     Ravens
    1.15
    claw
    1.08
     Raven
    0.95
    Raven
    0.92
     Orioles
    0.83
    crow
    0.76
    DragonMagazine
    0.74
     Wings
    0.71
     raven
    0.70
    ettes
    0.70
    Activations Density 0.011%

    No Known Activations