© 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. 1-RES-JB
    11. 10280
    Prev
    Next
    INDEX
    Explanations

    names mentioned in the text, particularly the name "Crow"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Crow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idential
    -0.76
    ugal
    -0.74
    idency
    -0.73
    uated
    -0.71
     declass
    -0.71
    aternity
    -0.70
    ItemTracker
    -0.70
     glor
    -0.70
    ocratic
    -0.69
    itia
    -0.68
    POSITIVE LOGITS
     Crow
    1.39
    crow
    1.05
    bars
    0.99
    bats
    0.99
    bones
    0.97
    hawk
    0.96
    vine
    0.92
    bone
    0.91
    shaw
    0.89
    der
    0.84
    Activations Density 0.009%

    No Known Activations