INDEX

Explanations

phrases related to a person's history or past performance

oai_token-act-pair · gpt-3.5-turbo

terms related to someone's performance or history, particularly in terms of accountability or reliability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

adin

-0.80

tein

-0.76

creen

-0.73

essel

-0.71

istani

-0.71

gyn

-0.70

hap

-0.70

sci

-0.69

 cart

-0.68

utterstock

-0.67

POSITIVE LOGITS

 record

0.97

record

0.93

 breaker

0.83

 Record

0.81

breaking

0.80

 Breaker

0.73

 holder

0.71

 achievement

0.68

keeping

0.66

inances

0.65

Activations Density 0.026%

phrases related to a person's history or past performance

terms related to someone's performance or history, particularly in terms of accountability or reliability

No Comments

No Known Activations