INDEX

Explanations

adverbs and adjectives indicating certainty or emphasis

oai_token-act-pair · gpt-3.5-turbo

words that indicate certainty, timing, or tendency

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

Negative Logits

 Doing

-0.75

izont

-0.72

 Aware

-0.66

imen

-0.64

 Continuing

-0.64

YING

-0.63

 Writing

-0.63

arter

-0.63

encing

-0.63

onding

-0.61

POSITIVE LOGITS

 existed

1.26

 belonged

1.18

 happened

1.12

 resembled

1.11

 resided

1.06

 belongs

1.06

 happens

1.06

 resembles

1.05

 exists

1.04

 lasted

1.00

Activations Density 0.162%

adverbs and adjectives indicating certainty or emphasis

words that indicate certainty, timing, or tendency

No Known Activations