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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3351
    Prev
    Next
    INDEX
    Explanations

    words related to the Swahili language

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific suffixes or syllable patterns in words

    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
    fully
    -0.96
     Likely
    -0.73
    ikarp
    -0.71
    fulness
    -0.67
    ruff
    -0.67
    marked
    -0.66
    tail
    -0.66
     Ober
    -0.66
    rip
    -0.65
    full
    -0.65
    POSITIVE LOGITS
    ibi
    1.32
    DragonMagazine
    0.85
    selage
    0.84
    ibo
    0.82
    vernment
    0.79
    ÄŁ
    0.77
    ose
    0.76
     crane
    0.73
    eva
    0.73
    ocl
    0.72
    Activations Density 0.011%

    No Known Activations