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. 22505
    Prev
    Next
    INDEX
    Explanations

    phrases related to starting or taking action on something

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their associations with actions or states

    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
    LY
    -0.65
     Liang
    -0.63
    theless
    -0.60
    Begin
    -0.58
     Lang
    -0.58
    chief
    -0.58
     omission
    -0.58
    ]}
    -0.57
    Berry
    -0.57
     Bulg
    -0.57
    POSITIVE LOGITS
    issions
    0.75
    retty
    0.75
    utters
    0.75
    ez
    0.74
    anan
    0.73
    entary
    0.73
    /+
    0.73
    itary
    0.72
     traction
    0.70
    izont
    0.70
    Activations Density 0.090%

    No Known Activations