INDEX

Explanations

mentions of geopolitical entities and political figures

oai_token-act-pair · gpt-3.5-turbo

terms related to political and governmental entities

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

Ô

-0.70

thood

-0.69

thia

-0.67

chwitz

-0.64

ombat

-0.64

ĸļ

-0.64

xual

-0.63

cycles

-0.61

hops

-0.61

atown

-0.60

POSITIVE LOGITS

 bureau

0.94

 agency

0.83

 equivalent

0.81

 secretary

0.75

 industry

0.72

 watchdog

0.71

 version

0.71

 department

0.71

 interpreter

0.71

 playbook

0.71

Activations Density 0.621%

mentions of geopolitical entities and political figures

terms related to political and governmental entities

No Comments

No Known Activations