© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    6. 17478
    Prev
    Next
    INDEX
    Explanations

    phrases related to clearing or cleaning up physical or metaphorical situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "clearing" or removing obstacles

    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
    ENTS
    -0.71
    ENCE
    -0.65
    nv
    -0.64
    sson
    -0.62
    atility
    -0.61
    ties
    -0.61
    ingo
    -0.61
    Lenin
    -0.59
     Kardash
    -0.59
    uates
    -0.59
    POSITIVE LOGITS
     waivers
    0.97
    houses
    0.95
    house
    0.88
     skies
    0.85
     clutter
    0.83
    ewater
    0.81
     rubble
    0.80
    cuts
    0.79
    brush
    0.79
     throat
    0.76
    Activations Density 0.040%

    No Known Activations