INDEX

Explanations

topics related to targeting or aimed actions

oai_token-act-pair · gpt-3.5-turbo

references to the term "targeted" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ilts

-0.79

SourceFile

-0.77

Else

-0.74

unts

-0.73

fo

-0.73

thus

-0.72

Struct

-0.71

BuyableInstoreAndOnline

-0.71

YC

-0.69

Import

-0.69

POSITIVE LOGITS

 targeted

1.42

 targets

1.23

 targeting

1.23

 target

1.04

oided

0.95

 prey

0.92

target

0.87

ads

0.78

 victims

0.77

 unsuspecting

0.75

Activations Density 0.008%

topics related to targeting or aimed actions

references to the term "targeted" in various contexts

No Comments

No Known Activations