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. 708
    Prev
    Next
    INDEX
    Explanations

    words with 'fl' followed by other letters, potentially related to food items

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "fl" in various contexts

    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
    hood
    -0.66
     Skydragon
    -0.64
     Beware
    -0.64
    RAL
    -0.63
    MENTS
    -0.62
     pleas
    -0.61
     messenger
    -0.60
    illas
    -0.60
     Nightmares
    -0.60
    MENT
    -0.59
    POSITIVE LOGITS
    oyd
    1.32
    owers
    1.28
    uffy
    1.28
    avored
    1.27
    oppy
    1.23
    ickr
    1.20
    avour
    1.16
    orescent
    1.10
    urry
    1.10
    utters
    1.09
    Activations Density 0.025%

    No Known Activations