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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 6717
    Prev
    Next
    INDEX
    Explanations

    words related to the geographical or directional center

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "cent" and its variations, indicating a focus on monetary or centennial themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ABE
    -0.85
    ãģį
    -0.79
    lihood
    -0.70
    è¦ļéĨĴ
    -0.68
    IGHTS
    -0.68
    manship
    -0.66
    IDES
    -0.64
    ettings
    -0.63
    OOD
    -0.63
    ãģĦ
    -0.63
    POSITIVE LOGITS
    ennial
    1.42
    imet
    1.42
    enary
    1.38
    uries
    1.30
    rals
    1.21
    imeter
    1.20
    urion
    1.19
    imeters
    1.17
    aur
    1.12
    RAL
    1.11
    Activations Density 0.045%

    No Known Activations