INDEX

Explanations

instances of the word "assuming"

oai_token-act-pair · gpt-3.5-turbo

phrases that express hypothetical situations or assumptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

btn

-0.64

jer

-0.61

lde

-0.60

ricular

-0.60

ãĤ·

-0.60

 logo

-0.59

othy

-0.58

 flare

-0.57

zens

-0.56

Ã¨

-0.56

POSITIVE LOGITS

 assuming

3.59

Assuming

2.06

 Assuming

2.01

 assume

2.00

assuming

1.97

 assumes

1.96

 assumption

1.62

 assum

1.61

 assumed

1.57

 excluding

1.54

Activations Density 0.019%

instances of the word "assuming"

phrases that express hypothetical situations or assumptions

No Comments

No Known Activations