© 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. 7-RES-JB
    11. 19518
    Prev
    Next
    INDEX
    Explanations

    Spanish words with accents on the letter 'o'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or word variant, likely indicative of a particular language or cultural reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orial
    -0.79
    uality
    -0.74
    achine
    -0.72
    ovie
    -0.72
    engers
    -0.71
    pread
    -0.69
    aimon
    -0.68
    ory
    -0.68
    ulse
    -0.67
    etsk
    -0.66
    POSITIVE LOGITS
    rien
    1.04
    atl
    0.84
    ··
    0.80
    ng
    0.79
    ð
    0.76
    rio
    0.76
    ÃįÃį
    0.75
    s
    0.74
    stan
    0.74
    vernment
    0.73
    Activations Density 0.025%

    No Known Activations