INDEX

Explanations

phrases related to identifying or emphasizing a necessity or requirement

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "need" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Surv

-0.70

selves

-0.65

 rabbit

-0.59

 Belg

-0.58

 Sheep

-0.58

 Shit

-0.58

Tit

-0.57

Zam

-0.57

 Zeit

-0.56

 Shut

-0.55

POSITIVE LOGITS

lessly

1.35

iness

0.93

iest

0.92

lest

0.88

ful

0.85

liest

0.80

lessness

0.80

INESS

0.80

iac

0.78

fully

0.78

Activations Density 0.039%

phrases related to identifying or emphasizing a necessity or requirement

mentions of the word "need" in various contexts

No Comments

No Known Activations