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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 18697
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and information dissemination

    oai_token-act-pair · gpt-3.5-turbo

    instances of common phrases and connectors in discourse

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

    No Comments

    Negative Logits
     Rover
    -0.69
     Moss
    -0.67
     Starg
    -0.65
     assassins
    -0.65
     Peaks
    -0.61
     Sas
    -0.61
     Clay
    -0.60
    CHAT
    -0.58
     Mirage
    -0.58
     moss
    -0.58
    POSITIVE LOGITS
     sidx
    0.86
    Downloadha
    0.81
    erous
    0.80
    imentary
    0.74
    é¾įå
    0.71
    orah
    0.71
    rative
    0.68
    together
    0.68
    maxwell
    0.67
    ionic
    0.67
    Activations Density 0.501%

    No Known Activations