© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6730
    Prev
    Next
    INDEX
    Explanations

    terms related to different influential factors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various contributing factors or influences in different 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
    vironment
    -0.81
    alach
    -0.81
    dos
    -0.80
    ocry
    -0.78
    CHAT
    -0.78
    phis
    -0.75
    retch
    -0.75
    esc
    -0.74
    velt
    -0.72
    kay
    -0.71
    POSITIVE LOGITS
     influencing
    1.17
     contributing
    1.09
     factors
    1.07
     factor
    1.05
     affecting
    0.99
     impacting
    0.98
     determining
    0.97
     Factors
    0.89
    factor
    0.88
     motivating
    0.88
    Activations Density 0.038%

    No Known Activations