INDEX

Explanations

terms related to political revolts or uprisings

oai_token-act-pair · gpt-3.5-turbo

terms related to uprisings and revolts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

illac

-0.90

ewater

-0.85

uchin

-0.77

estone

-0.76

othy

-0.72

orem

-0.70

ilk

-0.70

ramer

-0.69

Travel

-0.69

players

-0.67

POSITIVE LOGITS

 uprising

1.07

 revolt

1.02

 rebellion

0.96

 insurrection

0.92

 insurgency

0.92

 revol

0.88

 against

0.87

rained

0.86

 rebell

0.82

 insurg

0.82

Activations Density 0.032%

terms related to political revolts or uprisings

terms related to uprisings and revolts

No Comments

No Known Activations