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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 14566
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparation or readiness

    oai_token-act-pair · gpt-3.5-turbo

    future or conditional phrases denoting the state of being or outcomes

    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
    osate
    -0.69
     theorem
    -0.64
     disorder
    -0.63
     Extension
    -0.62
     Stain
    -0.62
     guise
    -0.60
     srfAttach
    -0.60
     Implementation
    -0.59
    strous
    -0.58
     expire
    -0.58
    POSITIVE LOGITS
     able
    1.66
     amazed
    1.24
     tempted
    1.19
     glad
    1.18
     thankful
    1.15
     ashamed
    1.11
     surprised
    1.11
     unable
    1.07
     afraid
    1.05
     aware
    1.05
    Activations Density 0.160%

    No Known Activations