INDEX

Explanations

phrases related to Imperial entities, especially universities and historical contexts

oai_token-act-pair · gpt-3.5-turbo

references to "Imperial" and related variations in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.91

earance

-0.78

rooms

-0.72

âķĲâķĲ

-0.71

THER

-0.68

lessly

-0.66

days

-0.66

chel

-0.66

gger

-0.65

ARB

-0.64

POSITIVE LOGITS

perial

1.00

ity

0.77

 Stout

0.74

gul

0.73

0.71

ITED

0.71

ist

0.69

ism

0.69

shire

0.67

oun

0.65

Activations Density 0.029%

phrases related to Imperial entities, especially universities and historical contexts

references to "Imperial" and related variations in the text

No Comments

No Known Activations