INDEX

Explanations

mentions of flaws and weaknesses

oai_token-act-pair · gpt-3.5-turbo

terms related to flaws and deficiencies

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

rollers

-0.76

Ń·

-0.70

 Carbuncle

-0.68

iversary

-0.67

ista

-0.66

fleet

-0.66

eston

-0.65

da

-0.64

xon

-0.63

stad

-0.62

POSITIVE LOGITS

 flaws

0.95

 plag

0.90

 flaw

0.88

 weaknesses

0.86

acies

0.85

lessly

0.82

 inherent

0.79

ulence

0.77

 deficiencies

0.76

 Hussein

0.76

Activations Density 0.055%

mentions of flaws and weaknesses

terms related to flaws and deficiencies

No Comments

No Known Activations