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. 9-RES-JB
    6. 7669
    Prev
    Next
    INDEX
    Explanations

    instances of the word "already" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating past accomplishments or actions

    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
    channelAvailability
    -0.81
    case
    -0.77
    rent
    -0.77
    especially
    -0.72
    catentry
    -0.66
    rus
    -0.64
     weap
    -0.64
    Reviewer
    -0.63
    upper
    -0.63
    pi
    -0.62
    POSITIVE LOGITS
     begun
    1.31
     undergone
    1.30
     been
    1.20
     gotten
    1.05
     surpassed
    1.05
     proven
    1.04
     embarked
    1.00
     succumbed
    0.99
     tasted
    0.98
     proved
    0.97
    Activations Density 0.032%

    No Known Activations