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. 7-RES-JB
    6. 7749
    Prev
    Next
    INDEX
    Explanations

    phrases involving multiple roles or functions assumed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    connective phrases and terms relating to comparisons or dualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioxide
    -0.80
    ombs
    -0.73
    nces
    -0.71
    ancies
    -0.70
     Bullets
    -0.70
     Moines
    -0.69
    rences
    -0.67
    utations
    -0.66
    abouts
    -0.66
    atoes
    -0.65
    POSITIVE LOGITS
     protector
    0.87
     discipl
    0.81
     append
    0.79
     unworthy
    0.77
     deserving
    0.76
     honorary
    0.75
     fodder
    0.75
    Compan
    0.72
     mascot
    0.72
     confid
    0.72
    Activations Density 0.413%

    No Known Activations