© 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. 7-RES-JB
    11. 17778
    Prev
    Next
    INDEX
    Explanations

    phrases related to transmission of information or energy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of transmission in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anova
    -0.88
    ãĥĦ
    -0.74
     Bav
    -0.69
    ghazi
    -0.68
     Alban
    -0.68
    glers
    -0.67
    Boss
    -0.66
     Gall
    -0.66
    Enough
    -0.65
    ucket
    -0.65
    POSITIVE LOGITS
     transmission
    1.02
     transmissions
    0.98
     electron
    0.88
     transmitted
    0.85
    metry
    0.84
    forward
    0.76
     Transmission
    0.75
     fluids
    0.75
     tracing
    0.74
     transmit
    0.70
    Activations Density 0.030%

    No Known Activations