INDEX

Explanations

blunt and frank language

oai_token-act-pair · gpt-3.5-turbo

words associated with directness and straightforwardness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Haunted

-0.81

Mich

-0.77

ITNESS

-0.75

————————————————

-0.75

————————

-0.74

YL

-0.74

 Occupations

-0.73

CF

-0.73

Cour

-0.71

SEC

-0.71

POSITIVE LOGITS

 blunt

1.40

odox

0.93

 nodd

0.87

 frank

0.84

entimes

0.80

 skew

0.80

 parting

0.77

 blasts

0.74

ãĤ©

0.74

 disse

0.73

Activations Density 0.008%

blunt and frank language

words associated with directness and straightforwardness

No Comments

No Known Activations