INDEX

Explanations

the word "decision"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "decision."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ingers

-0.79

amina

-0.72

 additive

-0.71

hern

-0.68

ubric

-0.67

orsi

-0.67

hemat

-0.67

vae

-0.66

izont

-0.66

atomic

-0.65

POSITIVE LOGITS

 makers

0.93

 decisions

0.92

 decision

0.91

 maker

0.75

 stance

0.71

 regarding

0.70

 ACTIONS

0.70

making

0.69

 calculus

0.68

 decided

0.67

Activations Density 0.033%

the word "decision"

instances of the word "decision."

No Known Activations