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. 10-RES-JB
    6. 18260
    Prev
    Next
    INDEX
    Explanations

    locations or names preceded by a dash '-' and then followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    names or references related to places and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saras
    -0.81
     destro
    -0.78
     Slayer
    -0.78
     655
    -0.78
     Pag
    -0.76
    åĮ
    -0.74
     Imag
    -0.72
     blender
    -0.71
     princ
    -0.71
     Pilot
    -0.70
    POSITIVE LOGITS
    es
    1.39
    ec
    1.35
    ez
    1.29
    ë
    1.27
    eb
    1.25
    eson
    1.25
    ek
    1.21
    és
    1.19
    ey
    1.19
    e
    1.18
    Activations Density 0.129%

    No Known Activations