Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22753
    Prev
    Next
    INDEX
    Explanations

    strings related to Equifax or the Equator

    oai_token-act-pair · gpt-3.5-turbo

    references to encryption and security protocols

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

    No Comments

    Negative Logits
     spare
    -0.67
    Ò
    -0.65
     fiction
    -0.65
    ãģ¦
    -0.65
    doms
    -0.64
     puff
    -0.64
     living
    -0.63
    stal
    -0.63
     Decay
    -0.63
     sten
    -0.62
    POSITIVE LOGITS
    ifax
    1.40
    ivalent
    1.30
    ilibrium
    1.18
    ipment
    1.18
    ilib
    1.11
    als
    1.09
    ivil
    1.06
    itable
    1.03
    iola
    1.02
    ienced
    0.99
    Activations Density 0.012%

    No Known Activations