INDEX

Explanations

phrases related to acknowledging or recognizing something

oai_token-act-pair · gpt-3.5-turbo

references to recognition of various issues and challenges

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

ipop

-0.75

inion

-0.70

icles

-0.68

etry

-0.67

llan

-0.67

ado

-0.67

escription

-0.66

umbnails

-0.65

edin

-0.65

 roundup

-0.64

POSITIVE LOGITS

 limitations

1.11

 risks

1.06

 seriousness

1.06

 dangers

1.00

 shortcomings

1.00

 importance

0.99

 realities

0.99

 weaknesses

0.98

 nuances

0.96

 strengths

0.94

Activations Density 0.295%

phrases related to acknowledging or recognizing something

references to recognition of various issues and challenges

No Comments

No Known Activations