INDEX

Explanations

words related to political figures and their actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the character "Ļ"

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

 disadvant

-0.77

undown

-0.73

 Participation

-0.70

 adolesc

-0.70

 tabloid

-0.70

 Palestin

-0.70

 Lawn

-0.65

 Folk

-0.65

 distractions

-0.65

 decimal

-0.65

POSITIVE LOGITS

ï¸ı

0.97

mir

0.90

felt

0.88

sure

0.85

lean

0.84

strong

0.83

forth

0.82

else

0.81

Balt

0.81

mand

0.80

Activations Density 0.378%

words related to political figures and their actions

occurrences of the character "Ļ"

No Comments

No Known Activations