© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 13767
    Prev
    Next
    INDEX
    Explanations

    terms related to causing obstacles or hindrances

    oai_token-act-pair · gpt-3.5-turbo

    references to hindrances or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URES
    -0.75
    URE
    -0.70
    terday
    -0.65
     Occupations
    -0.65
     Corinth
    -0.64
    orious
    -0.63
     Dame
    -0.63
    inia
    -0.62
     Cardinal
    -0.61
    itutional
    -0.60
    POSITIVE LOGITS
    ilton
    1.23
    strings
    1.09
    pering
    1.07
    stead
    1.03
    sters
    1.02
    bled
    1.01
    pton
    0.98
    mers
    0.97
    bell
    0.96
    ming
    0.92
    Activations Density 0.017%

    No Known Activations