INDEX

Explanations

phrases or words indicative of severe criticism or negative judgment

oai_token-act-pair · gpt-3.5-turbo

adjectives and phrases that express strong criticism or negativity towards individuals or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rir

-0.81

yles

-0.74

aden

-0.74

olina

-0.73

roo

-0.73

cycles

-0.72

ratom

-0.72

esville

-0.71

ubes

-0.70

ymes

-0.68

POSITIVE LOGITS

ãĥ£

0.90

0.87

 critiques

0.85

 quotes

0.84

 indictment

0.83

 judgement

0.80

 rebuke

0.78

 judgment

0.78

 critique

0.78

 reviews

0.77

Activations Density 0.039%

phrases or words indicative of severe criticism or negative judgment

adjectives and phrases that express strong criticism or negativity towards individuals or events

No Comments

No Known Activations