INDEX

Explanations

mentions of limitations or constraints

oai_token-act-pair · gpt-3.5-turbo

references to various forms of limitations and constraints

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

psc

-0.88

dan

-0.83

rone

-0.76

lynn

-0.75

cow

-0.73

DA

-0.72

inis

-0.72

agne

-0.71

oho

-0.70

TPP

-0.70

POSITIVE LOGITS

 limitations

0.88

 loopholes

0.86

 constraints

0.84

 inherent

0.82

 imposed

0.81

 limitation

0.77

 simultane

0.77

 drawback

0.75

 constraint

0.74

 weaknesses

0.73

Activations Density 0.040%

mentions of limitations or constraints

references to various forms of limitations and constraints

No Comments

No Known Activations