INDEX

Explanations

instances of negative events or controversies related to individuals

oai_token-act-pair · gpt-3.5-turbo

phrases related to allegations, accusations, or legal disputes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

endif

-0.55

...)

-0.53

 Magicka

-0.52

cube

-0.52

 Morty

-0.50

":"/

-0.50

 Appears

-0.50

whatever

-0.49

?:

-0.49

 Languages

-0.49

POSITIVE LOGITS

 unsuccessfully

0.65

 allegedly

0.60

 unsuccessful

0.57

 sidelined

0.55

 constituents

0.55

 deemed

0.54

 deem

0.52

 constituent

0.52

itially

0.52

 mistakenly

0.51

Activations Density 1.306%

instances of negative events or controversies related to individuals

phrases related to allegations, accusations, or legal disputes

No Comments

No Known Activations