INDEX

Explanations

concepts related to logic and reasoning

oai_token-act-pair · gpt-3.5-turbo

words related to reasoning or logical conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

avorite

-0.92

ibaba

-0.78

 Carbuncle

-0.76

 helicop

-0.69

omez

-0.67

estial

-0.64

 livest

-0.63

 stocking

-0.62

itals

-0.61

tein

-0.61

POSITIVE LOGITS

abl

1.28

why

0.96

ably

0.94

boards

0.79

¨

0.75

 justifying

0.75

Ľ

0.74

why

0.72

finding

0.72

reason

0.72

Activations Density 0.029%

concepts related to logic and reasoning

words related to reasoning or logical conclusions

No Comments

No Known Activations