INDEX

Explanations

words related to reduction and decrease

oai_token-act-pair · gpt-3.5-turbo

terms related to environmental emissions reduction

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

gerald

-0.69

Us

-0.67

Bet

-0.66

Â¯Â¯

-0.65

UB

-0.62

DN

-0.62

RIP

-0.61

è

-0.60

Mir

-0.59

 Prix

-0.58

POSITIVE LOGITS

itized

0.84

cember

0.84

ist

0.81

ascus

0.79

xual

0.78

ħĭ

0.78

jriwal

0.75

anguage

0.75

etheless

0.75

oshenko

0.75

Activations Density 0.023%

words related to reduction and decrease

terms related to environmental emissions reduction

No Comments

No Known Activations