© 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
    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. 19794
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpreting information or texts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interpret" and its variations, indicating a focus on the act of interpretation

    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
     Empires
    -0.76
     Indust
    -0.73
    ventus
    -0.73
    hart
    -0.71
    Interstitial
    -0.70
    trap
    -0.70
     Rath
    -0.66
    nih
    -0.65
    ccoli
    -0.63
    moon
    -0.63
    POSITIVE LOGITS
     interpret
    1.15
     Interpret
    1.10
     interpretation
    1.07
     interpretations
    1.06
     interpreting
    1.03
     interpre
    1.00
     meanings
    0.87
    notations
    0.82
     misinterpret
    0.82
    atively
    0.81
    Activations Density 0.029%

    No Known Activations