INDEX

Explanations

references to reports containing statistical data and analysis

oai_token-act-pair · gpt-3.5-turbo

references to reports and official documents

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

 ILCS

-0.72

ardless

-0.67

cale

-0.66

ventus

-0.63

afety

-0.62

OPA

-0.61

 brill

-0.61

;;;;

-0.60

TPPStreamerBot

-0.59

ompl

-0.59

POSITIVE LOGITS

 concludes

1.06

 cites

0.94

 adds

0.92

 cited

0.92

 summarizes

0.91

 quoted

0.85

 concluded

0.85

 acknowledges

0.85

 says

0.83

 directs

0.83

Activations Density 0.187%

references to reports containing statistical data and analysis

references to reports and official documents

No Comments

No Known Activations