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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 18287
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of completing a task or achieving a goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating common occurrences or trends affecting society

    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
    $.
    -0.55
     thereof
    -0.53
     respectively
    -0.53
    %.
    -0.52
     etc
    -0.52
     thereby
    -0.51
     outwe
    -0.50
    yond
    -0.49
    soever
    -0.49
    '."
    -0.49
    POSITIVE LOGITS
     nutshell
    0.65
     FANTASY
    0.51
    ?:
    0.47
     irony
    0.45
     WEEK
    0.45
     @
    0.45
    âĦ¢:
    0.45
     understatement
    0.45
     partName
    0.44
    ':
    0.43
    Activations Density 2.330%

    No Known Activations