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. 8-RES-JB
    6. 17297
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong beliefs or predictions

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility and capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CTR
    -0.65
     Arcade
    -0.64
     Steps
    -0.63
     Indie
    -0.62
     Goods
    -0.61
     Provided
    -0.60
     palms
    -0.60
     BG
    -0.58
     mats
    -0.58
    olor
    -0.57
    POSITIVE LOGITS
    lement
    0.94
    urious
    0.83
    nt
    0.82
    mint
    0.79
    ered
    0.78
    't
    0.78
    elt
    0.76
    anism
    0.75
    nir
    0.75
    scl
    0.74
    Activations Density 0.145%

    No Known Activations