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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 22725
    Prev
    Next
    INDEX
    Explanations

    profanity and insults directed towards others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initially
    -0.81
    Initially
    -0.74
    nown
    -0.74
    Events
    -0.70
    Sources
    -0.69
    Contents
    -0.67
    seekers
    -0.66
     Initially
    -0.66
    IAS
    -0.66
    Orig
    -0.65
    POSITIVE LOGITS
     goddamn
    1.37
     bunch
    1.26
     fucking
    1.21
     shitty
    1.18
     fuckin
    1.18
     damn
    1.17
     godd
    1.14
     dick
    1.09
     crappy
    1.05
     freaking
    1.01
    Activations Density 0.394%

    No Known Activations