INDEX

Explanations

generic phrases referring to a significant or noteworthy aspect

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize certainty or definitive statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

pak

-0.76

content

-0.73

agram

-0.71

tg

-0.70

ascript

-0.70

igation

-0.70

Filename

-0.67

tu

-0.67

endars

-0.66

ãĤ¦

-0.65

POSITIVE LOGITS

 abundantly

0.82

 undeniable

0.81

 indis

0.78

 bothers

0.78

 stands

0.78

 stood

0.77

 struck

0.75

 constant

0.73

 universally

0.72

 nutshell

0.72

Activations Density 0.113%

generic phrases referring to a significant or noteworthy aspect

phrases that emphasize certainty or definitive statements

No Comments

No Known Activations