© 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. 8-RES-JB
    11. 978
    Prev
    Next
    INDEX
    Explanations

    instances of the word "also" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "also" that indicate additional information or connections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASE
    -0.73
    ichen
    -0.67
     Closing
    -0.62
     Ready
    -0.61
     Scream
    -0.59
     Ascension
    -0.59
     Sor
    -0.58
     Trib
    -0.58
     Continuing
    -0.58
    winter
    -0.58
    POSITIVE LOGITS
     includes
    1.01
     coincides
    0.99
     coincided
    0.95
     reflects
    0.94
     reflected
    0.90
     incorporates
    0.90
     helps
    0.85
     contains
    0.85
     meant
    0.84
     included
    0.84
    Activations Density 0.082%

    No Known Activations