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. 10-RES-JB
    6. 17209
    Prev
    Next
    INDEX
    Explanations

    phrases related to doing something without a particular requirement or step

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ease of access or removal of barriers in various contexts

    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
    aez
    -0.79
    Topic
    -0.68
    eden
    -0.67
    ERG
    -0.66
     whistlebl
    -0.66
    neutral
    -0.65
    kees
    -0.65
    oulos
    -0.64
    Fair
    -0.63
    cellent
    -0.62
    POSITIVE LOGITS
     cumbersome
    1.28
     anymore
    1.26
     costly
    1.15
     bulky
    1.14
     unnecessarily
    1.14
     expensive
    1.08
     manually
    0.99
     tedious
    0.95
     nor
    0.92
     pesky
    0.91
    Activations Density 0.385%

    No Known Activations