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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 21590
    Prev
    Next
    INDEX
    Explanations

    phrases related to required actions or resources

    oai_token-act-pair · gpt-3.5-turbo

    words related to requirements and necessities

    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
    atever
    -0.77
    ierre
    -0.73
    ttle
    -0.71
    actionDate
    -0.69
    udeau
    -0.69
    adier
    -0.68
    otonin
    -0.66
    pan
    -0.64
    ookie
    -0.64
    ensional
    -0.63
    POSITIVE LOGITS
     herein
    0.89
     therein
    0.89
     thereto
    0.75
     incurred
    0.75
     contained
    0.72
     encountered
    0.69
     spawned
    0.67
     determines
    0.67
     emanating
    0.66
     afforded
    0.65
    Activations Density 0.242%

    No Known Activations