INDEX

Explanations

words related to ideologies or belief systems

oai_token-act-pair · gpt-3.5-turbo

terms related to political ideologies and movements, particularly those associated with anarchism and socialism

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

haar

-0.76

robe

-0.72

VPN

-0.70

IRD

-0.70

ËĪ

-0.69

rum

-0.68

UTF

-0.68

mire

-0.67

gat

-0.67

bsite

-0.67

POSITIVE LOGITS

ity

1.08

ities

0.90

ized

0.84

Pwr

0.84

ization

0.80

ical

0.80

arial

0.79

itÃ©

0.76

abama

0.75

otine

0.73

Activations Density 0.020%

words related to ideologies or belief systems

terms related to political ideologies and movements, particularly those associated with anarchism and socialism

No Comments

No Known Activations