INDEX

Explanations

words related to misrepresentation or misrepresentation itself

oai_token-act-pair · gpt-3.5-turbo

terms related to misrepresentation and its nuances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ï¸

-0.69

STON

-0.69

mith

-0.69

\\\\\\\\\\\\\\\\

-0.68

pei

-0.64

cius

-0.63

WAYS

-0.63

 nerv

-0.63

vantage

-0.62

creen

-0.61

POSITIVE LOGITS

ation

1.62

ations

1.51

ed

1.21

ing

1.03

ated

1.01

ating

0.99

eering

0.98

atives

0.98

ational

0.97

edly

0.95

Activations Density 0.036%

words related to misrepresentation or misrepresentation itself

terms related to misrepresentation and its nuances

No Comments

No Known Activations