INDEX

Explanations

phrases that indicate the probability or likelihood of an event occurring

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Архівовано

-0.64

حياتها

-0.59

 متعلقه

-0.58

出版年

-0.56

Skocz

-0.55

medriver

-0.55

 nahilalakip

-0.52

,'\

-0.51

."],

-0.51

camento

-0.51

POSITIVE LOGITS

Soon

0.88

 Soon

0.86

Odds

0.78

 odds

0.76

 Odds

0.74

 washed

0.74

odds

0.70

odd

0.69

 soon

0.66

LabelTagHelper

0.65

Activations Density 0.140%

phrases that indicate the probability or likelihood of an event occurring

No Comments

No Known Activations