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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15503
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or objects above the ground

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term 'overhead' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifying
    -0.96
    ifies
    -0.96
    ifier
    -0.94
    ifiable
    -0.92
    eming
    -0.90
    ifiers
    -0.87
    ified
    -0.83
    orian
    -0.79
    ELY
    -0.77
    atche
    -0.77
    POSITIVE LOGITS
     overhead
    1.11
     crane
    0.90
     projector
    0.78
     lobe
    0.74
     fees
    0.74
     bins
    0.73
    cuts
    0.72
     flap
    0.70
     detach
    0.69
    lift
    0.67
    Activations Density 0.019%

    No Known Activations