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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 14453
    Prev
    Next
    INDEX
    Explanations

    phrases related to going through difficult or challenging situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating experiences of hardship or struggle

    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
    iom
    -0.79
    CVE
    -0.74
    join
    -0.71
    intend
    -0.70
    resso
    -0.66
    inet
    -0.66
    Sport
    -0.65
    ether
    -0.63
    caster
    -0.63
    ially
    -0.62
    POSITIVE LOGITS
     puberty
    1.33
     phases
    1.16
     hardships
    0.98
     stages
    0.97
     hoops
    0.96
     periods
    0.94
     adolescence
    0.94
     motions
    0.93
     ordeal
    0.92
    uberty
    0.89
    Activations Density 0.065%

    No Known Activations