INDEX

Explanations

keywords related to comparing or emphasizing something that already exists or happened

oai_token-act-pair · gpt-3.5-turbo

words indicating continuity or repetition over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĺħ

-0.74

 Laos

-0.73

java

-0.69

 Rica

-0.68

 Cambodia

-0.66

"""

-0.65

 Tycoon

-0.65

 Isle

-0.65

 Challenges

-0.65

eday

-0.64

POSITIVE LOGITS

 unprotected

0.79

 unstable

0.72

 unch

0.72

 volatile

0.71

 combust

0.71

 unin

0.70

 uncomp

0.70

 rebellious

0.69

protected

0.68

 eclectic

0.68

Activations Density 0.215%

keywords related to comparing or emphasizing something that already exists or happened

words indicating continuity or repetition over time

No Comments

No Known Activations