© 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. 1-RES-JB
    11. 9370
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of technology

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "te" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.70
     Corruption
    -0.70
    DragonMagazine
    -0.70
     Hawks
    -0.68
    etheless
    -0.67
     isEnabled
    -0.67
     CVE
    -0.66
    âķIJ
    -0.65
     seats
    -0.64
    espie
    -0.63
    POSITIVE LOGITS
    legram
    1.13
    legraph
    1.02
    achable
    0.96
    pee
    0.95
     te
    0.93
    quila
    0.92
    levision
    0.86
    eming
    0.85
    zza
    0.84
    uning
    0.84
    Activations Density 0.004%

    No Known Activations