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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22990
    Prev
    Next
    INDEX
    Explanations

    social media hashtags

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "host" and its variations, indicating a focus on hosting or host-related content

    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
    ht
    -0.79
    lahoma
    -0.79
    hu
    -0.72
    iso
    -0.70
    auga
    -0.70
    ks
    -0.70
    itary
    -0.67
    opol
    -0.67
    it
    -0.67
    ista
    -0.66
    POSITIVE LOGITS
    LY
    1.28
    GROUND
    1.25
    INGS
    1.18
     IMAGES
    1.18
    ULAR
    1.17
    INE
    1.17
    OUT
    1.15
    INESS
    1.13
    BOOK
    1.13
    NAME
    1.12
    Activations Density 0.049%

    No Known Activations