INDEX

Explanations

phrases containing the word "targeted."

oai_token-act-pair · gpt-3.5-turbo

the term "targeted" in various contexts related to actions or groups being affected

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

fo

-0.80

SourceFile

-0.77

batch

-0.71

rar

-0.71

Else

-0.70

shire

-0.68

aut

-0.67

STRUCT

-0.66

maid

-0.65

lycer

-0.64

POSITIVE LOGITS

 targets

0.93

 targeting

0.93

ted

0.81

 targeted

0.80

 squarely

0.79

 killings

0.77

 target

0.76

ads

0.73

oided

0.73

eers

0.72

Activations Density 0.023%

phrases containing the word "targeted."

the term "targeted" in various contexts related to actions or groups being affected

No Comments

No Known Activations