INDEX

Explanations

references to time durations such as "decades" and "years."

oai_token-act-pair · gpt-3.5-turbo

references to time durations, specifically "decades" and "years."

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

burning

-0.67

dr

-0.63

venge

-0.58

ãĤ´ãĥ³

-0.57

Baby

-0.57

cause

-0.57

fo

-0.57

him

-0.56

Miami

-0.56

because

-0.55

POSITIVE LOGITS

 however

0.81

 meanwhile

0.80

 there

0.68

 though

0.63

kson

0.60

we

0.60

lance

0.59

idents

0.58

 Peaks

0.55

IRC

0.55

Activations Density 0.220%

references to time durations such as "decades" and "years."

references to time durations, specifically "decades" and "years."

No Comments

No Known Activations