© 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. 10764
    Prev
    Next
    INDEX
    Explanations

    terms related to communication methods and technologies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of conjunctions and prepositions typically used in discussions about communication methods

    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
    worthy
    -0.84
    equality
    -0.74
     Dise
    -0.70
     Rebell
    -0.70
    slaught
    -0.69
    ior
    -0.68
     Spo
    -0.67
     Conserv
    -0.67
     patri
    -0.66
     Races
    -0.66
    POSITIVE LOGITS
     fax
    1.54
     telephone
    1.52
     texting
    1.42
     Skype
    1.39
    Fax
    1.39
     phone
    1.35
    fax
    1.27
     email
    1.27
     cellphone
    1.26
     SMS
    1.25
    Activations Density 0.182%

    No Known Activations