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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17497
    Prev
    Next
    INDEX
    Explanations

    phrases that include hyphenated compound words

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations or themes related to adversity or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dickinson
    -0.83
    ulhu
    -0.76
     Lumpur
    -0.75
     Compass
    -0.74
     Rica
    -0.73
     Bohem
    -0.69
     Shooter
    -0.69
     Cache
    -0.68
     Chero
    -0.68
     Scully
    -0.68
    POSITIVE LOGITS
    connected
    1.15
    sized
    1.11
    exclusive
    1.11
    focused
    1.07
    defined
    1.06
    serving
    1.05
    protected
    1.05
    equ
    1.04
    function
    1.04
    interest
    1.03
    Activations Density 0.079%

    No Known Activations