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. 18849
    Prev
    Next
    INDEX
    Explanations

    proper nouns seemingly related to actors, characters, or productions, particularly focused on "Kaufman" and "Crane."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of a specific character's name

    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
    xon
    -0.74
    MpServer
    -0.68
    CHO
    -0.68
    Balt
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
     Lumia
    -0.61
    ãĥ³ãĤ¸
    -0.61
     pus
    -0.61
    Interstitial
    -0.61
    senal
    -0.60
    POSITIVE LOGITS
    erent
    1.11
    irms
    1.01
    mpeg
    1.00
    ords
    1.00
    ees
    0.98
    erences
    0.96
    rey
    0.93
    erential
    0.91
    etch
    0.90
    iculty
    0.90
    Activations Density 0.014%

    No Known Activations