Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18079
    Prev
    Next
    INDEX
    Explanations

    the concept of something happening in a specific physical location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in front."

    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
    cci
    -0.81
    chini
    -0.80
    ixtape
    -0.68
    redited
    -0.68
    ulet
    -0.68
    yssey
    -0.67
     Strait
    -0.66
    ajor
    -0.65
    zie
    -0.65
    atto
    -0.65
    POSITIVE LOGITS
    aday
    0.82
    matter
    0.74
     row
    0.70
    office
    0.70
    woods
    0.69
    iers
    0.68
    runners
    0.68
    most
    0.66
    ed
    0.66
    stadt
    0.65
    Activations Density 0.010%

    No Known Activations