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. 7-RES-JB
    6. 15923
    Prev
    Next
    INDEX
    Explanations

    surnames specifically the name "Paramatta"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ram" in various contexts

    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
     Carib
    -0.67
    âĸº
    -0.62
     predic
    -0.60
     Yankee
    -0.60
     indifference
    -0.58
    \<
    -0.58
     accord
    -0.57
     decomp
    -0.56
     hypoc
    -0.56
     Dangerous
    -0.55
    POSITIVE LOGITS
    irez
    1.17
    ming
    1.14
    bler
    1.05
    mers
    1.05
    matical
    1.03
    pton
    1.03
    atic
    1.00
    bling
    0.98
    blers
    0.96
    icro
    0.93
    Activations Density 0.026%

    No Known Activations