© 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. 2-RES-JB
    11. 998
    Prev
    Next
    INDEX
    Explanations

    the word "right" in various contexts

    oai_token-act-pair · gpt-4-turbo

    the word "right" used in a positive or affirmative context

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or agreements expressed through the word "right."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mat
    -0.71
    ripp
    -0.68
    ĸļ
    -0.68
    odium
    -0.64
    ulative
    -0.64
    ains
    -0.62
    otin
    -0.62
     Clarke
    -0.61
    kel
    -0.61
     srfAttach
    -0.61
    POSITIVE LOGITS
    eous
    1.11
     wing
    0.87
    terday
    0.81
    wing
    0.80
     forearm
    0.79
    shore
    0.76
     winger
    0.71
    ward
    0.70
    move
    0.69
     aligned
    0.68
    Activations Density 0.053%

    No Known Activations