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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 2280
    Prev
    Next
    INDEX
    Explanations

    verbs in the imperative form, particularly phrases that include the words "should have been able to help."

    oai_token-act-pair · gpt-3.5-turbo

    biblical or archaic language expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.79
    VPN
    -0.75
    ADRA
    -0.71
     Miliband
    -0.65
    omsky
    -0.65
     Cantor
    -0.64
    INESS
    -0.63
    irtual
    -0.63
    METHOD
    -0.63
     ADS
    -0.61
    POSITIVE LOGITS
    nen
    0.79
     passer
    0.68
     conductor
    0.66
    eous
    0.63
    stown
    0.63
     pokemon
    0.63
    tons
    0.62
     wrestler
    0.62
    ochond
    0.61
     mosa
    0.61
    Activations Density 0.000%

    No Known Activations