INDEX

Explanations

phrases related to indicating additional information or actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "also" that indicate additional information or clarification

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pering

-0.75

jam

-0.74

click

-0.70

ouses

-0.67

agus

-0.66

Bang

-0.65

Bind

-0.63

AGES

-0.62

bound

-0.62

Flight

-0.61

POSITIVE LOGITS

 optionally

0.89

 occasionally

0.87

 intermitt

0.82

 anecd

0.78

 cautioned

0.77

 briefly

0.76

 noteworthy

0.75

 contend

0.74

 incidentally

0.74

 indirectly

0.74

Activations Density 0.112%

phrases related to indicating additional information or actions

instances of the word "also" that indicate additional information or clarification

No Comments

No Known Activations