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. 6-RES-JB
    6. 13044
    Prev
    Next
    INDEX
    Explanations

    phrases related to dependency and reliance

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing conditions or factors that are contingent or dependent on something else

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vision
    -0.86
    ãĥīãĥ©
    -0.81
    ãĥİ
    -0.75
    tha
    -0.72
    ãĥ¼ãĥ³
    -0.72
    ãĥŃ
    -0.72
    ãĥĪ
    -0.72
    jc
    -0.71
    åħ
    -0.70
     Panc
    -0.69
    POSITIVE LOGITS
     upon
    0.83
     critically
    0.82
    ymm
    0.81
     heavily
    0.81
    awaru
    0.80
    ancy
    0.76
     substant
    0.73
    ants
    0.70
     veter
    0.69
    ministic
    0.69
    Activations Density 0.021%

    No Known Activations