© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22776
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social figures

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the Salafi movement and its prominent figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Halls
    -0.82
    brates
    -0.80
    naire
    -0.79
    esville
    -0.74
    seys
    -0.70
    itialized
    -0.70
     Winged
    -0.69
    mart
    -0.69
    holm
    -0.69
    bone
    -0.69
    POSITIVE LOGITS
    afi
    0.90
    qs
    0.89
    ornia
    0.84
    ÄŁ
    0.81
    zzle
    0.81
    qus
    0.79
    rient
    0.79
     Ezek
    0.77
    req
    0.77
    q
    0.73
    Activations Density 0.011%

    No Known Activations