INDEX

Explanations

words related to quotations or statements

oai_token-act-pair · gpt-3.5-turbo

variants of the word "is" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mint

-0.70

 hunts

-0.62

rouse

-0.62

cob

-0.61

 otherwise

-0.61

 disse

-0.61

 vulner

-0.60

 resorts

-0.60

 caravan

-0.60

 tides

-0.59

POSITIVE LOGITS

[+

0.77

%"

0.75

 Parenthood

0.73

 Angels

0.68

rael

0.68

Pak

0.67

kaya

0.67

 Beir

0.67

utter

0.66

 Coming

0.66

Activations Density 0.160%

words related to quotations or statements

variants of the word "is" in various contexts

No Comments

No Known Activations