© 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. 2-RES-JB
    6. 18868
    Prev
    Next
    INDEX
    Explanations

    references to the term "juvenile" or related words

    oai_token-act-pair · gpt-3.5-turbo

    references to juvenile individuals and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.80
    zzle
    -0.78
    cross
    -0.76
    ombs
    -0.74
    igslist
    -0.72
    ding
    -0.70
    zyme
    -0.70
    sheets
    -0.69
    itsch
    -0.69
    aeda
    -0.68
    POSITIVE LOGITS
     delinqu
    1.42
     delinquent
    1.18
     Juven
    0.98
     juveniles
    0.93
     juvenile
    0.92
     offenders
    0.90
     detention
    0.82
     Gohan
    0.78
     males
    0.77
     Males
    0.77
    Activations Density 0.011%

    No Known Activations