© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6997
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Federico"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific company or brand

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

    No Comments

    Negative Logits
    mable
    -0.76
    ĸļ
    -0.76
    ting
    -0.75
    gling
    -0.73
    nah
    -0.71
    luck
    -0.69
    ENTION
    -0.68
    stall
    -0.66
    ANG
    -0.65
    topic
    -0.65
    POSITIVE LOGITS
    zzi
    1.08
    verage
    0.93
    zzle
    0.88
    ffee
    0.81
    emia
    0.80
    leans
    0.79
    atl
    0.79
    cephal
    0.76
    ographically
    0.74
    vernment
    0.74
    Activations Density 0.012%

    No Known Activations