INDEX

Explanations

phrases related to successful outcomes or achievements

oai_token-act-pair · gpt-3.5-turbo

the phrase "pay off" in various contexts, particularly related to outcomes or results

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

 pigeon

-0.77

 polarized

-0.69

atin

-0.68

 Fram

-0.65

©¶æ

-0.65

PG

-0.63

BuyableInstoreAndOnline

-0.63

ffe

-0.63

cpp

-0.63

relative

-0.62

POSITIVE LOGITS

 handsome

0.85

beat

0.69

IFT

0.69

ulz

0.68

IELD

0.67

ments

0.67

 dividends

0.66

yx

0.65

 dearly

0.64

ASC

0.64

Activations Density 0.015%

phrases related to successful outcomes or achievements

the phrase "pay off" in various contexts, particularly related to outcomes or results

No Comments

No Known Activations