INDEX

Explanations

adverbs that modify actions with a positive connotation

oai_token-act-pair · gpt-3.5-turbo

adverbs that describe manner or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enf

-0.68

eries

-0.62

ilater

-0.61

hao

-0.61

 totally

-0.61

rite

-0.61

 privilege

-0.60

 outright

-0.60

 willfully

-0.58

ado

-0.57

POSITIVE LOGITS

 enough

0.90

 throughout

0.86

 thereafter

0.84

enough

0.84

tics

0.77

utics

0.74

 into

0.74

 during

0.74

 ILCS

0.73

 afterwards

0.73

Activations Density 0.159%

adverbs that modify actions with a positive connotation

adverbs that describe manner or intensity

No Comments

No Known Activations