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. 9-RES-JB
    6. 555
    Prev
    Next
    INDEX
    Explanations

    words related to news alerts and special reports

    oai_token-act-pair · gpt-3.5-turbo

    alerts and notifications related to news events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monop
    -0.70
     coerc
    -0.64
     bene
    -0.61
    ivas
    -0.60
    theless
    -0.57
    itar
    -0.56
     scapego
    -0.55
     grate
    -0.54
     Sas
    -0.54
     Sloan
    -0.54
    POSITIVE LOGITS
    legram
    0.67
    ricanes
    0.65
    email
    0.63
    weather
    0.63
    enos
    0.62
     subscribing
    0.59
    readable
    0.59
     à¤
    0.59
    rill
    0.58
    urations
    0.58
    Activations Density 0.018%

    No Known Activations