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. 9825
    Prev
    Next
    INDEX
    Explanations

    keywords related to the conclusion or finalization of something, as well as terms related to secure communication and transactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that end with the word "end"

    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
     acidic
    -0.65
     Aure
    -0.64
     Dou
    -0.62
    BLIC
    -0.60
     Digest
    -0.60
     Mister
    -0.59
     unusual
    -0.57
     Oath
    -0.56
     Courage
    -0.56
     brothers
    -0.56
    POSITIVE LOGITS
    owment
    1.53
    angering
    1.43
    ocrin
    1.23
    ocrine
    1.20
    angers
    1.16
    orph
    1.11
    angered
    1.09
    eared
    1.05
    game
    1.03
    ogeneity
    1.02
    Activations Density 0.055%

    No Known Activations