© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17081
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal structures and systems

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    added
    -0.72
    vec
    -0.67
    Adds
    -0.65
    cms
    -0.61
    java
    -0.61
    ali
    -0.59
    gest
    -0.59
     Recomm
    -0.59
    uph
    -0.59
    requires
    -0.59
    POSITIVE LOGITS
     consequently
    0.87
     others
    0.83
    rogen
    0.81
     other
    0.79
    rogens
    0.78
     therefore
    0.75
     subsequent
    0.71
     vice
    0.68
     consequ
    0.67
     assorted
    0.62
    Activations Density 0.236%

    No Known Activations