INDEX

Explanations

phrases expressing opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

expressions of belief or opinion

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĺ

-0.68

Guard

-0.66

OTO

-0.63

 starring

-0.61

uminum

-0.61

panic

-0.61

anni

-0.60

 Himself

-0.60

NetMessage

-0.60

Grade

-0.59

POSITIVE LOGITS

 ourselves

1.17

 ours

0.90

our

0.83

 unres

0.68

 fostering

0.68

 strongly

0.68

onen

0.67

roud

0.64

 rigorous

0.64

 delighted

0.63

Activations Density 0.273%

phrases expressing opinions or beliefs

expressions of belief or opinion

No Comments

No Known Activations