INDEX

Explanations

opportunities or instances where opportunities are mentioned

oai_token-act-pair · gpt-3.5-turbo

references to opportunities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

SO

-0.69

geries

-0.64

arre

-0.62

Dispatch

-0.62

eros

-0.61

ModLoader

-0.61

DATA

-0.61

head

-0.60

bey

-0.60

arling

-0.59

POSITIVE LOGITS

 afforded

1.07

 presented

0.96

 opportunities

0.89

 opportunity

0.85

llor

0.80

 arise

0.78

 Opportun

0.74

 conferred

0.74

 arises

0.74

 arose

0.73

Activations Density 0.065%

opportunities or instances where opportunities are mentioned

references to opportunities

No Comments

No Known Activations