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. 7-RES-JB
    6. 16310
    Prev
    Next
    INDEX
    Explanations

    non-standard unicode characters, possibly related to specific formatting or data representation

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to various subjects

    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
     oath
    -1.03
     prosec
    -0.89
     liaison
    -0.81
     amph
    -0.79
     silenced
    -0.79
     arming
    -0.78
     subpoena
    -0.77
     persuasion
    -0.77
     greeting
    -0.75
     act
    -0.75
    POSITIVE LOGITS
    Average
    1.32
    Percent
    1.22
    Overall
    1.19
    Among
    1.18
    Compared
    1.17
    Statistics
    1.15
    About
    1.10
    Meanwhile
    1.10
    Between
    1.09
    Numbers
    1.09
    Activations Density 0.600%

    No Known Activations