© 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. 8-RES-JB
    11. 6083
    Prev
    Next
    INDEX
    Explanations

    names of places that have the word "Nuevo" in them

    oai_token-act-pair · gpt-3.5-turbo

    the substring "ue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atform
    -0.91
    intosh
    -0.74
    aceutical
    -0.70
    arna
    -0.65
    ifications
    -0.65
    icum
    -0.65
    acl
    -0.64
    ows
    -0.62
    Agg
    -0.61
    olid
    -0.60
    POSITIVE LOGITS
    lla
    1.31
    llo
    1.10
    hler
    1.08
    ll
    1.00
    lling
    0.99
    lly
    0.97
    llers
    0.96
    lled
    0.94
    lder
    0.94
    hner
    0.91
    Activations Density 0.038%

    No Known Activations