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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 15815
    Prev
    Next
    INDEX
    Explanations

    phrases related to being deceived or misled

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to deception and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nant
    -0.65
     occupation
    -0.63
     genesis
    -0.61
     refinement
    -0.61
     township
    -0.59
     Sutherland
    -0.57
    perture
    -0.57
     Supervisor
    -0.57
     Representatives
    -0.56
     roundup
    -0.55
    POSITIVE LOGITS
     aback
    1.12
     irresist
    1.04
     by
    0.84
    illusion
    0.75
    isp
    0.74
     anew
    0.72
     wondering
    0.72
    whel
    0.71
     into
    0.68
    By
    0.68
    Activations Density 0.233%

    No Known Activations