INDEX

Explanations

phrases related to comparisons and evaluations in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

وى

-0.51

 part

-0.48

 Spring

-0.46

tily

-0.46

osan

-0.46

ynx

-0.46

 Fund

-0.44

 consumer

-0.44

taya

-0.44

 vigor

-0.43

POSITIVE LOGITS

 AspNetCore

0.98

 Infórmanos

0.89

principalColumn

0.88

tvguidetime

0.77

 useAppContext

0.75

показания

0.74

хьтан

0.74

 للمعارف

0.73

 désolés

0.72

+#+#

0.72

Activations Density 1.940%

phrases related to comparisons and evaluations in research contexts

No Comments

No Known Activations