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. 9-RES-JB
    6. 6486
    Prev
    Next
    INDEX
    Explanations

    words related to upward movement or progression

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ascension or rising in status or power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meal
    -0.70
     gallery
    -0.67
     Squid
    -0.65
    bytes
    -0.65
    Ò
    -0.65
     Hart
    -0.63
     Bastard
    -0.62
     Shakespeare
    -0.61
     Baird
    -0.60
     Hebdo
    -0.60
    POSITIVE LOGITS
    ribed
    1.26
    ribing
    1.22
    ension
    1.21
    endant
    1.14
    ribe
    1.09
    riber
    0.99
    endants
    0.94
    ensible
    0.94
    ribes
    0.93
    ript
    0.89
    Activations Density 0.082%

    No Known Activations