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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1656
    Prev
    Next
    INDEX
    Explanations

    names that likely belong to entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the syllable "en."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hitch
    -0.75
     Orbit
    -0.66
    TPPStreamerBot
    -0.64
     pole
    -0.63
     flats
    -0.62
     shake
    -0.61
     reconc
    -0.60
     bumper
    -0.59
     Pell
    -0.58
     pumpkin
    -0.58
    POSITIVE LOGITS
    chant
    1.19
    emies
    1.13
    riched
    1.11
    viron
    1.09
    zyme
    1.09
    esis
    1.07
    ema
    1.07
    igmat
    1.00
    zel
    0.96
    abling
    0.95
    Activations Density 0.027%

    No Known Activations