© 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. 1-RES-JB
    6. 23012
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person named "Mamma" with varying levels of relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the term "alma" in various contexts

    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
    OFF
    -0.80
     shortest
    -0.71
    GoldMagikarp
    -0.71
    DOWN
    -0.69
    Recomm
    -0.67
    Interview
    -0.66
    worldly
    -0.66
     Asheville
    -0.64
    APE
    -0.63
     hazards
    -0.63
    POSITIVE LOGITS
    ppa
    1.05
    pling
    0.99
    ignt
    0.97
    estro
    0.97
    olean
    0.95
    qua
    0.89
    esthes
    0.89
    uthor
    0.89
    uble
    0.85
    ma
    0.84
    Activations Density 0.007%

    No Known Activations