INDEX

Explanations

words related to reasons or causes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "cause" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Seasons

-0.74

illet

-0.64

 Storm

-0.63

OSE

-0.62

iants

-0.62

alos

-0.60

 Winds

-0.60

Ku

-0.60

ian

-0.58

 surplus

-0.58

POSITIVE LOGITS

 cele

1.42

way

1.06

cause

0.91

 celeb

0.88

ways

0.83

ality

0.80

why

0.73

unity

0.70

why

0.69

llor

0.69

Activations Density 0.037%

words related to reasons or causes

occurrences of the word "cause" and its variations in context

No Comments

No Known Activations