© 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. 2-RES-JB
    11. 23505
    Prev
    Next
    INDEX
    Explanations

    phrases related to the word "Hamm", which could be a name, place, or other entity

    oai_token-act-pair · gpt-3.5-turbo

    references to "Hamm" and "mammoth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.89
    fulness
    -0.77
    sembly
    -0.76
    lycer
    -0.74
    nder
    -0.74
    nces
    -0.73
    nergy
    -0.72
    sers
    -0.72
    krit
    -0.71
    lves
    -0.71
    POSITIVE LOGITS
     Mamm
    1.06
    olit
    0.95
    oths
    0.88
     Hamb
    0.86
    ush
    0.79
    arella
    0.76
    umm
    0.75
    ocaly
    0.74
    aths
    0.73
    urg
    0.73
    Activations Density 0.016%

    No Known Activations