© 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. 21853
    Prev
    Next
    INDEX
    Explanations

    specific measurements such as units of length or size

    oai_token-act-pair · gpt-3.5-turbo

    references to sizes or measurements

    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
    isms
    -0.80
    ãĤ´ãĥ³
    -0.79
    affles
    -0.66
    oping
    -0.65
    theless
    -0.65
    alist
    -0.64
    hey
    -0.63
    selves
    -0.63
    emo
    -0.61
    ationally
    -0.61
    POSITIVE LOGITS
     diameter
    1.25
     total
    1.13
     length
    1.05
     duration
    1.03
     advance
    0.98
    verts
    0.97
     circumference
    0.95
     succession
    0.89
     front
    0.88
    versions
    0.87
    Activations Density 0.080%

    No Known Activations