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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17686
    Prev
    Next
    INDEX
    Explanations

    government or organizational documents or reports

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" and other contextual elements related to it

    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
    dh
    -0.73
    enment
    -0.69
    issance
    -0.67
    pee
    -0.66
    ieties
    -0.65
    oslav
    -0.64
     Samoa
    -0.64
    nesday
    -0.64
     Dying
    -0.62
     dh
    -0.62
    POSITIVE LOGITS
     median
    0.81
     hottest
    0.69
     unmist
    0.68
     likelihood
    0.64
     recept
    0.63
     disproportion
    0.62
     chars
    0.61
     fingerprints
    0.61
     hairs
    0.61
    actly
    0.60
    Activations Density 0.370%

    No Known Activations