INDEX

Explanations

phrases related to misinformation and manipulation for political or personal gain

oai_token-act-pair · gpt-3.5-turbo

instances of deception or misleading information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

atonin

-0.81

ipeg

-0.80

ridor

-0.79

ixel

-0.78

cade

-0.78

ftime

-0.76

utra

-0.76

pring

-0.75

 Aires

-0.75

enhagen

-0.73

POSITIVE LOGITS

 misplaced

1.09

 incompetent

1.08

 deceit

1.07

 misunderstood

1.07

 inadequ

1.05

 misrepresent

1.03

 inept

0.99

 illeg

0.98

 unworthy

0.98

 misleading

0.98

Activations Density 0.355%

phrases related to misinformation and manipulation for political or personal gain

instances of deception or misleading information

No Comments

No Known Activations