INDEX

Explanations

text related to software release notes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "notes."

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

cross

-0.70

 cruc

-0.70

ILLE

-0.69

izont

-0.67

WAY

-0.65

LOS

-0.65

 waged

-0.62

duct

-0.60

 advoc

-0.59

 indignation

-0.58

POSITIVE LOGITS

notes

1.03

 Notes

0.93

ynthesis

0.85

 Gained

0.84

ets

0.82

ppelin

0.82

ense

0.82

books

0.80

heet

0.79

asures

0.79

Activations Density 0.029%

text related to software release notes

occurrences of the word "notes."

No Comments

No Known Activations