© 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
    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. 21623
    Prev
    Next
    INDEX
    Explanations

    Asymmetrical patterns or structures

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to asymmetry and symmetry in scientific contexts

    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
     ado
    -0.74
    GER
    -0.73
     regards
    -0.66
    house
    -0.64
     eyes
    -0.63
     WEEK
    -0.62
     Wik
    -0.60
     Movie
    -0.60
    Footnote
    -0.59
     Companion
    -0.59
    POSITIVE LOGITS
    etrical
    2.06
    etric
    1.94
    etr
    1.53
    etry
    1.51
    et
    1.20
    inately
    1.16
    eties
    1.14
    inate
    1.13
    etic
    1.05
    acies
    1.04
    Activations Density 0.055%

    No Known Activations