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. 18308
    Prev
    Next
    INDEX
    Explanations

    terms related to sour taste

    oai_token-act-pair · gpt-3.5-turbo

    references to sourness in various 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
    ITNESS
    -0.85
    ulhu
    -0.81
    UAL
    -0.77
    Constructed
    -0.76
    alach
    -0.68
    ervation
    -0.68
    atched
    -0.67
    avior
    -0.66
    inct
    -0.64
    judicial
    -0.64
    POSITIVE LOGITS
    cery
    1.02
     grapes
    1.01
    bean
    1.00
     sour
    0.89
    dy
    0.88
    beans
    0.85
    fruit
    0.81
    cup
    0.81
    ness
    0.77
    der
    0.76
    Activations Density 0.019%

    No Known Activations