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. 7-RES-JB
    6. 5800
    Prev
    Next
    INDEX
    Explanations

    statements indicating loss or decline

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to loss or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.78
    Loading
    -0.76
    Iss
    -0.72
    UNCH
    -0.72
    ocument
    -0.70
    AY
    -0.70
    GGGGGGGG
    -0.68
    VEL
    -0.68
     Mous
    -0.67
    yang
    -0.67
    POSITIVE LOGITS
     footing
    1.20
     own
    1.14
     virginity
    1.10
     grip
    1.00
     grasp
    0.97
     sanity
    0.96
     composure
    0.96
     rightful
    0.96
     bearings
    0.94
     foothold
    0.92
    Activations Density 0.116%

    No Known Activations