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. 10-RES-JB
    6. 23087
    Prev
    Next
    INDEX
    Explanations

    instances where individuals or groups publicly express their support or opposition to a specific cause or entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verbs "come" and "came" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    versions
    -0.65
    orage
    -0.65
    IELD
    -0.63
    olor
    -0.61
    ording
    -0.61
    itcher
    -0.60
    pak
    -0.60
    hap
    -0.59
    chance
    -0.58
    reality
    -0.57
    POSITIVE LOGITS
     forth
    1.02
     undone
    0.84
     forward
    0.81
     roaring
    0.73
     out
    0.72
     ashore
    0.72
    atories
    0.69
     knocking
    0.69
     charging
    0.67
     embroiled
    0.67
    Activations Density 0.056%

    No Known Activations