INDEX

Explanations

words related to political controversies and news reporting

oai_token-act-pair · gpt-3.5-turbo

phrases highlighting problems and critiques within studies or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

iership

-0.75

cend

-0.74

venge

-0.74

ivities

-0.74

 tranqu

-0.71

ikk

-0.71

 restless

-0.71

cipline

-0.71

duino

-0.70

 dreams

-0.70

POSITIVE LOGITS

 debunked

1.42

 misleading

1.38

 misrepresent

1.35

 inaccur

1.31

 debunk

1.21

 inaccurate

1.21

 omitted

1.19

emphasis

1.19

 inacc

1.18

 mislead

1.17

Activations Density 0.851%

words related to political controversies and news reporting

phrases highlighting problems and critiques within studies or reports

No Comments

No Known Activations