INDEX

Explanations

phrases related to political or official positions

oai_token-act-pair · gpt-3.5-turbo

references to bureaucratic or administrative contexts involving underlying issues or systemic criticisms

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

aceutical

-0.72

 Gaul

-0.71

jri

-0.67

agher

-0.66

chat

-0.65

 Flip

-0.61

arij

-0.61

raltar

-0.61

ophon

-0.61

ichael

-0.60

POSITIVE LOGITS

ãģĨ

0.76

EGIN

0.76

xual

0.74

ATCH

0.73

uary

0.73

OLD

0.72

riage

0.70

LECT

0.70

FontSize

0.69

IAL

0.68

Activations Density 0.058%

phrases related to political or official positions

references to bureaucratic or administrative contexts involving underlying issues or systemic criticisms

No Comments

No Known Activations