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. 4438
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a specific topic or concept as a point of discussion or relevance

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for that matter."

    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
    sbm
    -0.86
    omas
    -0.78
     Aad
    -0.71
     Mines
    -0.66
    ATER
    -0.65
    bern
    -0.64
    osponsors
    -0.64
    obal
    -0.63
     Vest
    -0.63
    kered
    -0.63
    POSITIVE LOGITS
     whatsoever
    0.80
     minded
    0.78
    ional
    0.76
    enance
    0.73
    tainment
    0.68
    awei
    0.68
    etheless
    0.67
    agine
    0.64
    ²¾
    0.63
    cules
    0.63
    Activations Density 0.008%

    No Known Activations