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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5554
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a topic or subject being discussed, such as "on the grounds of" or "on behalf of"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on" used in various contexts

    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
    Champ
    -0.73
    949
    -0.66
    MODE
    -0.65
    Mini
    -0.63
    rament
    -0.63
    ####
    -0.63
    Port
    -0.62
    OTS
    -0.61
    assium
    -0.61
    RL
    -0.61
    POSITIVE LOGITS
     behalf
    1.64
    erous
    1.33
     occasion
    1.26
    eday
    1.12
    etime
    1.11
    shore
    1.09
     occasions
    1.05
    eness
    1.05
    site
    1.05
    yx
    1.04
    Activations Density 0.302%

    No Known Activations