© 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. 9-RES-JB
    11. 22405
    Prev
    Next
    INDEX
    Explanations

    instances where the word "almost" is used

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "almost"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agate
    -0.75
    ACTED
    -0.72
     Dynamics
    -0.71
     sclerosis
    -0.71
     RTX
    -0.70
     Puzzles
    -0.65
    ä¸Ń
    -0.65
    endi
    -0.65
    ourses
    -0.64
    oran
    -0.63
    POSITIVE LOGITS
     certainly
    1.16
     exclusively
    0.90
     invariably
    0.83
     entirely
    0.80
     identical
    0.80
     surely
    0.80
     universally
    0.80
     definitely
    0.79
     unbelievably
    0.79
    certain
    0.78
    Activations Density 0.036%

    No Known Activations