INDEX

Explanations

phrases indicating a strong position or action taken in response to a situation

oai_token-act-pair · gpt-3.5-turbo

the verb "is" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 targ

-0.71

 goodbye

-0.63

—"

-0.61

,[

-0.59

 Meridian

-0.59

)|

-0.59

 peaks

-0.58

 qualification

-0.57

 badge

-0.57

 sweats

-0.56

POSITIVE LOGITS

etheless

1.23

ŃĶ

0.90

senal

0.85

ĸļ

0.84

Ļ½

0.79

 nonetheless

0.76

yip

0.73

 nevertheless

0.73

laun

0.71

::::::::

0.71

Activations Density 0.378%

phrases indicating a strong position or action taken in response to a situation

the verb "is" in different contexts

No Comments

No Known Activations