INDEX

Explanations

phrases indicating cause and effect

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" used in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

peria

-0.76

encing

-0.72

resa

-0.71

arty

-0.71

hyde

-0.70

auga

-0.70

arter

-0.70

rying

-0.70

zing

-0.67

zie

-0.67

POSITIVE LOGITS

 incidentally

0.80

 translates

0.77

pires

0.77

 happens

0.73

 turns

0.72

ãĤ©

0.72

 resembled

0.70

 frankly

0.68

 resembles

0.68

 turned

0.66

Activations Density 0.099%

phrases indicating cause and effect

occurrences of the word "in" used in various contexts

No Comments

No Known Activations