© 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. 1-RES-JB
    6. 23177
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs and teachings conflicting with external actions or words

    oai_token-act-pair · gpt-3.5-turbo

    references to contradictions of religious teachings or doctrines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebted
    -0.58
    ptives
    -0.57
    hooting
    -0.53
    enture
    -0.52
    agascar
    -0.51
    ividual
    -0.51
    culus
    -0.50
    ragon
    -0.50
    oyer
    -0.50
    âķIJ
    -0.49
    POSITIVE LOGITS
    ¶ħ
    0.63
     behav
    0.62
    76561
    0.61
    etheless
    0.60
     behavi
    0.59
     lifestyles
    0.55
    paio
    0.53
     lifestyle
    0.53
     multicultural
    0.52
     racial
    0.51
    Activations Density 5.064%

    No Known Activations