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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24168
    Prev
    Next
    INDEX
    Explanations

    financial, gaming, voting, identity verification, sport-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various activities, actions, and behaviors often associated with social or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknow
    -0.61
    hung
    -0.57
    nick
    -0.57
    ayed
    -0.57
    ays
    -0.54
    UG
    -0.54
    comment
    -0.54
    going
    -0.54
     pione
    -0.53
     sugg
    -0.53
    POSITIVE LOGITS
     whilst
    0.89
     while
    0.76
     abroad
    0.75
     wherever
    0.74
    enium
    0.73
     WITHOUT
    0.71
     cheaply
    0.70
     correctly
    0.69
     onstage
    0.69
     whenever
    0.67
    Activations Density 0.831%

    No Known Activations