INDEX

Explanations

sentences or statements ending with a comma and a non-zero activation value word

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol

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

 imagination

-0.81

 puff

-0.79

 stump

-0.78

 idea

-0.74

 likeness

-0.72

 resemblance

-0.71

 floppy

-0.69

è¦ļéĨĴ

-0.69

 shape

-0.67

izen

-0.66

POSITIVE LOGITS

ï¸ı

1.16

said

0.98

tra

0.92

Â¯

0.91

âĢł

0.85

#$

0.85

mr

0.81

Pg

0.81

east

0.81

ttp

0.81

Activations Density 0.206%

sentences or statements ending with a comma and a non-zero activation value word

instances of a specific character or symbol

No Comments

No Known Activations