© 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. 0-RES-JB
    11. 4091
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "octopus"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "opus"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     counseling
    -0.70
     homes
    -0.68
     warning
    -0.66
     safety
    -0.66
     Cert
    -0.65
     distance
    -0.65
     residences
    -0.65
     reminding
    -0.64
     remed
    -0.62
     areas
    -0.62
    POSITIVE LOGITS
    opus
    4.75
    opter
    1.14
    ebra
    1.14
    asus
    1.11
    ĸļ
    1.09
    ulhu
    1.09
    aurus
    1.06
     squid
    1.04
    iatus
    1.02
    opy
    1.00
    Activations Density 0.021%

    No Known Activations