INDEX

Explanations

words indicating conclusions, comparisons, or actions related to processes and changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Efq

-0.83

 raiſ

-0.76

 itſelf

-0.72

 myſelf

-0.72

 ſtate

-0.72

QMetaType

-0.71

 ftate

-0.70

 fevere

-0.69

 houſe

-0.67

 <=",

-0.67

POSITIVE LOGITS

AccessorTable

0.60

ardized

0.53

telt

0.51

sur

0.48

 فريبيس

0.47

retum

0.46

Bl

0.45

bula

0.45

xos

0.45

pl

0.44

Activations Density 1.117%

words indicating conclusions, comparisons, or actions related to processes and changes

No Comments

No Known Activations