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. 5513
    Prev
    Next
    INDEX
    Explanations

    email addresses or specific textual markers within a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to invalid or malfunctioning systems

    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
    urat
    -0.79
    halla
    -0.78
    Newsletter
    -0.78
    iary
    -0.74
    baum
    -0.72
    cation
    -0.71
    etheless
    -0.70
     stabilize
    -0.70
    soType
    -0.69
    fficiency
    -0.67
    POSITIVE LOGITS
    Liverpool
    0.86
    England
    0.82
    Actor
    0.82
     apologised
    0.81
     Yorkshire
    0.81
     Notting
    0.79
    Britain
    0.78
    Scotland
    0.78
     Belfast
    0.77
     rugby
    0.77
    Activations Density 0.063%

    No Known Activations