© 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. 20326
    Prev
    Next
    INDEX
    Explanations

    words related to critical or important aspects of a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with prediction, assessment, and evaluation processes

    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
     loves
    -0.69
     believes
    -0.67
     hopes
    -0.64
     regrets
    -0.64
    laughs
    -0.64
     argues
    -0.60
    ãĥ³ãĤ¸
    -0.60
    Adds
    -0.59
     likes
    -0.59
    OV
    -0.59
    POSITIVE LOGITS
     are
    1.36
     were
    1.35
     expire
    1.34
     arise
    1.28
     occur
    1.26
     exist
    1.24
     collide
    1.20
     aren
    1.19
    were
    1.17
     weren
    1.17
    Activations Density 0.308%

    No Known Activations