INDEX

Explanations

phrases related to additional information or details about a given topic

oai_token-act-pair · gpt-3.5-turbo

the word "also" used in various contexts throughout the document

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

stice

-0.76

Ott

-0.64

 Canaver

-0.64

Leave

-0.61

umbledore

-0.60

cuts

-0.60

iliate

-0.60

anth

-0.60

arms

-0.59

ision

-0.59

POSITIVE LOGITS

 considered

0.89

 notable

0.88

 noteworthy

0.86

 known

0.85

 priv

0.85

 implicated

0.83

 referred

0.82

 congratulated

0.80

 affected

0.80

 susceptible

0.80

Activations Density 0.077%

phrases related to additional information or details about a given topic

the word "also" used in various contexts throughout the document

No Comments

No Known Activations