INDEX

Explanations

percentages

oai_token-act-pair · gpt-3.5-turbo

percentage values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 purs

-0.72

wagen

-0.71

pload

-0.69

uyomi

-0.68

agate

-0.67

ipples

-0.67

 Antiqu

-0.67

ãĤ©

-0.66

rod

-0.65

 Juda

-0.64

POSITIVE LOGITS

1.05

%%

1.03

%%%%

0.89

percent

0.88

%-

0.84

(%

0.81

#$

0.77

rowth

0.75

NAME

0.75

NL

0.73

Activations Density 0.004%

percentages

percentage values

No Comments

No Known Activations