INDEX

Explanations

noun phrases that include the determiner "a."

oai_token-act-pair · gpt-3.5-turbo

the article "a" and its variations, indicating a focus on articles and descriptors 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

agents

-0.84

votes

-0.82

anism

-0.78

Attempts

-0.77

evidence

-0.75

 abuses

-0.75

encies

-0.74

blocks

-0.72

acid

-0.71

Americans

-0.70

POSITIVE LOGITS

 plethora

1.33

 bunch

1.20

 slew

1.17

 handful

1.17

lot

1.11

 multitude

1.10

 couple

1.04

cknowled

1.01

 variety

0.98

 sizeable

0.97

Activations Density 0.415%

noun phrases that include the determiner "a."

the article "a" and its variations, indicating a focus on articles and descriptors in various contexts

No Comments

No Known Activations