INDEX

Explanations

phrases mentioning specific names, likely related to political or social contexts

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly those named "Nad" and "Raf."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

chnology

-0.73

vernment

-0.70

FTWARE

-0.67

fare

-0.67

verage

-0.66

ODUCT

-0.64

 Unch

-0.61

ative

-0.60

ãĥĨ

-0.59

redits

-0.59

POSITIVE LOGITS

Nad

1.01

 Seym

0.87

inet

0.86

anian

0.82

quet

0.80

vich

0.78

ael

0.77

inished

0.76

ules

0.76

enta

0.75

Activations Density 0.039%

phrases mentioning specific names, likely related to political or social contexts

references to specific individuals, particularly those named "Nad" and "Raf."

No Comments

No Known Activations