© 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. 6621
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of 'op'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to octopuses and related biological concepts

    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
     Browne
    -0.62
     corrid
    -0.58
     Clarks
    -0.57
    âĸ¬âĸ¬
    -0.57
     grounds
    -0.56
     wolf
    -0.54
     wolves
    -0.54
     Beyond
    -0.54
     deceptive
    -0.53
     Gael
    -0.53
    POSITIVE LOGITS
    sych
    1.22
    neum
    1.19
    edia
    1.18
    hene
    1.15
    athetic
    1.14
    rint
    1.13
    olitical
    1.12
    ython
    1.09
    unct
    1.08
    odcast
    1.07
    Activations Density 0.047%

    No Known Activations