INDEX

Explanations

words relating to emphasizing a point or degree

oai_token-act-pair · gpt-3.5-turbo

the word "ever" in various contexts and forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

akings

-0.72

ophys

-0.67

 Instr

-0.67

hett

-0.67

 Ruin

-0.65

sembly

-0.63

 openings

-0.62

ĺħ

-0.62

assetsadobe

-0.62

emia

-0.61

POSITIVE LOGITS

theless

1.18

idge

1.03

lasting

0.96

ider

0.94

deen

0.81

ries

0.80

VER

0.76

ably

0.75

hood

0.74

iders

0.71

Activations Density 0.009%

words relating to emphasizing a point or degree

the word "ever" in various contexts and forms

No Comments

No Known Activations