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. 4-RES-JB
    6. 19254
    Prev
    Next
    INDEX
    Explanations

    text related to locations and directions

    oai_token-act-pair · gpt-3.5-turbo

    references to traffic and vehicle-related issues

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

    No Comments

    Negative Logits
     whilst
    -0.87
     civilisation
    -0.74
     analys
    -0.74
     cunt
    -0.71
    Firstly
    -0.69
     fulfil
    -0.69
     torture
    -0.68
     betray
    -0.67
    isations
    -0.67
     paed
    -0.67
    POSITIVE LOGITS
    Alert
    0.81
     Asheville
    0.79
     statewide
    0.79
    unicip
    0.78
    Oregon
    0.78
    insured
    0.76
     Downtown
    0.73
     Parkway
    0.72
    Portland
    0.71
     nonprofits
    0.71
    Activations Density 3.431%

    No Known Activations