INDEX

Explanations

mentions of the word "ny" with a high activation value

oai_token-act-pair · gpt-3.5-turbo

the presence of the term "ny" 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 @ 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

EMP

-0.83

rador

-0.74

Reviewed

-0.72

ModLoader

-0.69

INGTON

-0.68

ENTION

-0.67

ributes

-0.67

Spread

-0.67

IBLE

-0.66

ENDED

-0.66

POSITIVE LOGITS

mph

0.99

 Mellon

0.86

acht

0.85

ny

0.84

 Giuliani

0.81

heter

0.79

giene

0.77

cling

0.74

brook

0.73

die

0.72

Activations Density 0.020%

mentions of the word "ny" with a high activation value

the presence of the term "ny" in various contexts

No Comments

No Known Activations