© 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. 1994
    Prev
    Next
    INDEX
    Explanations

    words related to locations or landmarks with "hill" in the name

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "hill" and its variations in different 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
    URES
    -0.66
     unic
    -0.62
     chromos
    -0.62
    ften
    -0.62
     UR
    -0.61
    Ô
    -0.61
    ULAR
    -0.61
    eele
    -0.60
    glomer
    -0.59
    Protect
    -0.59
    POSITIVE LOGITS
    imore
    0.94
    hill
    0.88
    iard
    0.84
    hog
    0.82
    bush
    0.81
    dden
    0.80
    stein
    0.79
    rod
    0.78
    esley
    0.77
    arious
    0.76
    Activations Density 0.008%

    No Known Activations