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. 8-RES-JB
    6. 5522
    Prev
    Next
    INDEX
    Explanations

    phrases related to thwarted or failed actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fo," indicating a focus on specific grammatical or contextual cues

    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
     Colleges
    -0.65
     Redemption
    -0.63
    âĶģ
    -0.62
     Scholars
    -0.60
    Interstitial
    -0.60
     abiding
    -0.60
    lain
    -0.58
     regards
    -0.58
    lich
    -0.57
    lust
    -0.57
    POSITIVE LOGITS
    ogle
    1.12
    obar
    1.12
    LLOW
    1.11
    ortun
    1.10
    oster
    1.06
    etus
    1.06
    itness
    1.03
    avored
    1.03
    ils
    1.02
    isting
    1.00
    Activations Density 0.025%

    No Known Activations