INDEX

Explanations

phrases indicating different emotional states and situations like coldness, intelligence, and frustration

oai_token-act-pair · gpt-3.5-turbo

repetitions of the letter 'L' in various forms

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

 Palestin

-0.75

 succession

-0.71

 visualization

-0.70

geries

-0.69

 mathemat

-0.68

 incorpor

-0.68

 strained

-0.67

 overload

-0.65

 successive

-0.65

 fragmentation

-0.64

POSITIVE LOGITS

ï¸ı

0.81

ï¸

0.79

eal

0.78

vana

0.77

Â£

0.76

ttle

0.76

eries

0.74

ery

0.73

audi

0.72

surv

0.72

Activations Density 0.299%

phrases indicating different emotional states and situations like coldness, intelligence, and frustration

repetitions of the letter 'L' in various forms

No Comments

No Known Activations