Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15790
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criminal activity or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zan
    -0.44
    abad
    -0.44
     Nadu
    -0.42
    verbs
    -0.41
    versible
    -0.41
    tainment
    -0.40
    ELL
    -0.40
    GO
    -0.38
    OSED
    -0.37
    ANS
    -0.37
    POSITIVE LOGITS
     of
    1.57
    of
    1.22
    Of
    1.17
     Of
    1.16
     thereof
    1.16
     OF
    1.14
    OF
    0.88
    oft
    0.79
    ta
    0.60
    luster
    0.59
    Activations Density 2.505%

    No Known Activations