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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2299
    Prev
    Next
    INDEX
    Explanations

    words related to movement and physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    words ending in specific suffix patterns, particularly related to emotional or descriptive states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.69
    OTOS
    -0.66
    ãĥĨãĤ£
    -0.62
     Haram
    -0.61
    VI
    -0.60
     Zur
    -0.60
    Recomm
    -0.60
     Jav
    -0.59
    Myth
    -0.58
     WATCHED
    -0.58
    POSITIVE LOGITS
    ingly
    1.27
    ing
    1.14
    ishly
    0.99
    buck
    0.98
    iness
    0.93
    lust
    0.89
    puff
    0.89
    lessly
    0.89
    lings
    0.88
    orph
    0.87
    Activations Density 0.176%

    No Known Activations