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. 9595
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific type of equipment or product, likely related to technology or gaming

    oai_token-act-pair · gpt-3.5-turbo

    references to combination moves or strategies in games

    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
    mberg
    -0.74
    aniel
    -0.73
    aco
    -0.71
    oral
    -0.69
    ady
    -0.68
    unc
    -0.68
     Abraham
    -0.66
    sburg
    -0.65
     Wage
    -0.64
     Petty
    -0.63
    POSITIVE LOGITS
     Breaker
    0.91
    iques
    0.73
     breaker
    0.72
     boxes
    0.70
    ycle
    0.70
    halla
    0.70
     combo
    0.70
     between
    0.69
    -+-+
    0.69
     builder
    0.68
    Activations Density 0.016%

    No Known Activations