INDEX

Explanations

phrases related to reading instructions or information

oai_token-act-pair · gpt-3.5-turbo

the definite article "the" 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

 followed

-0.75

 whenever

-0.73

 respectively

-0.71

 namely

-0.65

Eva

-0.65

 whilst

-0.65

 shortly

-0.64

isin

-0.63

@@

-0.63

=#

-0.63

POSITIVE LOGITS

 slightest

1.77

 entirety

1.20

nor

1.15

 specifics

1.08

 anymore

1.07

 usual

1.06

 same

1.06

 totality

0.98

 confines

0.92

 merits

0.90

Activations Density 0.417%

phrases related to reading instructions or information

the definite article "the" in various contexts

No Comments

No Known Activations