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. 6-RES-JB
    6. 12740
    Prev
    Next
    INDEX
    Explanations

    words related to angular momentum and directives

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to directives and angular measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.87
    ername
    -0.83
    tu
    -0.79
    ells
    -0.78
    PER
    -0.75
    aho
    -0.75
    places
    -0.75
    keeping
    -0.74
    gins
    -0.74
    BIP
    -0.73
    POSITIVE LOGITS
    inho
    0.75
     Galile
    0.74
     nomine
    0.73
    issance
    0.66
    emouth
    0.66
    teenth
    0.66
     superpower
    0.65
     angular
    0.65
     oun
    0.64
     directives
    0.63
    Activations Density 0.039%

    No Known Activations