INDEX

Explanations

keywords related to making decisions or policies

oai_token-act-pair · gpt-3.5-turbo

instances of the word "adopt" in various forms and contexts

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

ibur

-0.66

othal

-0.65

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.65

isal

-0.64

OIL

-0.63

 istg

-0.62

hole

-0.61

oola

-0.59

imir

-0.58

 Templ

-0.58

POSITIVE LOGITS

 adopt

0.85

 adopted

0.84

 adopting

0.76

ively

0.74

 Viper

0.72

 adoption

0.72

irtual

0.68

mits

0.67

ivating

0.66

phrase

0.64

Activations Density 0.021%

keywords related to making decisions or policies

instances of the word "adopt" in various forms and contexts

No Comments

No Known Activations