INDEX

Explanations

words ending in "ing" or "ING"

oai_token-act-pair · gpt-3.5-turbo

gerunds and present participles 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

saf

-0.71

arant

-0.70

 culminating

-0.69

ĸļ

-0.68

imet

-0.64

irtual

-0.62

follow

-0.61

ranging

-0.61

seeing

-0.59

behind

-0.59

POSITIVE LOGITS

redients

1.05

LY

1.02

tons

0.90

 Yourself

0.82

 Agents

0.74

ulate

0.74

ments

0.72

encies

0.71

 agents

0.70

 oneself

0.70

Activations Density 0.216%

words ending in "ing" or "ING"

gerunds and present participles in various contexts

No Comments

No Known Activations