INDEX

Explanations

mentions of compromises or negotiations

oai_token-act-pair · gpt-3.5-turbo

references to compromise

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

ahon

-0.86

į

-0.75

asters

-0.72

vals

-0.71

lining

-0.71

stri

-0.70

Ĭ

-0.69

runner

-0.67

soon

-0.67

aina

-0.65

POSITIVE LOGITS

 compromise

0.92

 compromises

0.86

romising

0.84

 compromising

0.73

yip

0.68

 between

0.68

 breaker

0.67

 Bastard

0.67

 compromised

0.67

opian

0.66

Activations Density 0.021%

mentions of compromises or negotiations

references to compromise

No Comments

No Known Activations