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. 16693
    Prev
    Next
    INDEX
    Explanations

    sentences where someone has clearly expressed a point of view or made a statement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "make" and its variations in different contexts

    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
     Viper
    -0.70
    76561
    -0.67
    assis
    -0.65
    ---------
    -0.64
    Fram
    -0.62
     conditioning
    -0.60
    NESS
    -0.58
     stripe
    -0.58
     Slov
    -0.57
    heter
    -0.56
    POSITIVE LOGITS
    ailable
    0.99
     sure
    0.98
    hift
    0.91
    emort
    0.86
     landfall
    0.83
     headlines
    0.80
    ÄŁ
    0.78
    okane
    0.77
    ezvous
    0.76
    akedown
    0.76
    Activations Density 0.139%

    No Known Activations