INDEX

Explanations

method calls related to retrieving or checking values in data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 ویکی‌پدیا

-0.94

 صوتيه

-0.84

ItemLayout

-0.83

 Siro

-0.65

oğlu

-0.64

hind

-0.64

rocco

-0.61

 Baird

-0.61

ActionMode

-0.60

 Templeton

-0.60

POSITIVE LOGITS

get

0.74

weetened

0.68

 Heal

0.68

醐

0.66

NUMX

0.65

ALLEN

0.64

Ashlee

0.64

 heal

0.64

warf

0.63

هرست

0.63

Activations Density 0.031%

method calls related to retrieving or checking values in data structures

No Comments

No Known Activations