INDEX

Explanations

instances of the word "was" followed by other words in the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "was" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

currently

-0.72

icles

-0.66

wall

-0.65

 Current

-0.64

veland

-0.64

 Piercing

-0.63

otiation

-0.61

uras

-0.61

 Extend

-0.61

rouse

-0.61

POSITIVE LOGITS

hes

0.99

 instrumental

0.99

wolves

0.93

wolf

0.89

 mistaken

0.89

hers

0.81

 intentional

0.81

 careless

0.80

 intentionally

0.79

 negligent

0.79

Activations Density 0.403%

instances of the word "was" followed by other words in the text

instances of the word "was" in various contexts

No Comments

No Known Activations