INDEX

Explanations

words related to aggression

oai_token-act-pair · gpt-3.5-turbo

instances of the term "aggro" and its variations, indicating a focus on aggression or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

phrine

-0.72

 obser

-0.71

 Gemini

-0.68

 sights

-0.68

nsic

-0.66

fulness

-0.65

vironment

-0.65

 enactment

-0.63

isation

-0.60

ological

-0.59

POSITIVE LOGITS

regate

1.36

regation

1.07

rieved

1.06

aign

0.91

entric

0.87

alos

0.87

orno

0.86

staff

0.84

les

0.82

arette

0.80

Activations Density 0.042%

words related to aggression

instances of the term "aggro" and its variations, indicating a focus on aggression or conflict

No Comments

No Known Activations