INDEX

Explanations

references or calls to view or see something, often indicating importance or additional information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftance

-0.70

Grath

-0.70

knapp

-0.70

 Hoffman

-0.69

shaft

-0.66

 Wadsworth

-0.66

Alfredo

-0.65

 Alfredo

-0.64

Athens

-0.63

xter

-0.63

POSITIVE LOGITS

See

2.00

See

1.92

see

1.89

see

1.86

SEE

1.83

 Sees

1.73

 sees

1.67

SEE

1.61

sees

1.38

 seeing

1.30

Activations Density 0.084%

references or calls to view or see something, often indicating importance or additional information

No Comments

No Known Activations