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. 0-RES-JB
    6. 17645
    Prev
    Next
    INDEX
    Explanations

    terms related to colocalization in scientific contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "local."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weeds
    -0.76
     tumble
    -0.74
     Jane
    -0.72
    bags
    -0.72
     Vik
    -0.70
     apr
    -0.69
     rake
    -0.67
     MAT
    -0.65
     curse
    -0.65
     Vi
    -0.62
    POSITIVE LOGITS
    ocal
    4.71
    ocally
    2.44
    ocate
    1.16
    ibr
    1.15
    ohyd
    1.15
    ocation
    1.13
    oc
    1.12
    obar
    1.08
    anguage
    1.06
    ocus
    1.06
    Activations Density 0.019%

    No Known Activations