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. 23128
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases with specific patterns of characters

    oai_token-act-pair · gpt-3.5-turbo

    references to time and control events

    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
    ichick
    -0.68
    hens
    -0.63
    etsk
    -0.62
    lists
    -0.60
    vention
    -0.59
    asty
    -0.59
    onomous
    -0.59
    ach
    -0.59
    ittal
    -0.58
    ery
    -0.58
    POSITIVE LOGITS
     EDITION
    1.27
    HAM
    1.19
    URA
    1.17
    AGES
    1.14
    HEAD
    1.12
    MENT
    1.12
    WOR
    1.11
    LET
    1.11
    EY
    1.10
    WAR
    1.09
    Activations Density 0.251%

    No Known Activations