INDEX

Explanations

expressions of speculation, hypothesis, or conjecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.92

 myſelf

-0.91

Efq

-0.86

 חיצוניים

-0.85

 Cæsar

-0.84

 faſt

-0.82

 Monfieur

-0.81

 ſmall

-0.80

 ſever

-0.79

 Shakspeare

-0.79

POSITIVE LOGITS

 perhaps

0.62

 possibly

0.61

possibly

0.61

perhaps

0.58

may

0.57

 likely

0.57

 Possibly

0.56

 Perhaps

0.51

Possibly

0.50

Perhaps

0.49

Activations Density 0.479%

expressions of speculation, hypothesis, or conjecture

No Comments

No Known Activations