INDEX

Explanations

mentions of political figures or political issues

oai_token-act-pair · gpt-3.5-turbo

words related to political themes and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Carbuncle

-0.75

urat

-0.74

 Warrant

-0.73

 Shining

-0.73

 recall

-0.71

 pity

-0.71

 warrant

-0.67

Ved

-0.67

 glory

-0.66

URN

-0.65

POSITIVE LOGITS

icians

1.60

ician

1.47

ifact

1.35

ically

1.26

eness

1.18

icans

1.08

icking

1.05

ico

1.04

ique

1.02

itech

1.01

Activations Density 0.024%

mentions of political figures or political issues

words related to political themes and discussions

No Comments

No Known Activations