© 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. 10-RES-JB
    11. 21369
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating quantities or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.81
    hyde
    -0.68
    roller
    -0.63
    aci
    -0.63
    ãĥ´
    -0.61
    catentry
    -0.59
     conflic
    -0.58
     trave
    -0.58
    HO
    -0.58
    onder
    -0.58
    POSITIVE LOGITS
     100
    0.84
     10
    0.83
     twice
    0.83
     50
    0.82
     150
    0.82
     500
    0.81
     300
    0.80
     ½
    0.80
     1
    0.79
     200
    0.78
    Activations Density 0.092%

    No Known Activations