INDEX

Explanations

instances of the word "goal"

oai_token-act-pair · gpt-3.5-turbo

references to objectives or goals 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

BuyableInstoreAndOnline

-0.78

oute

-0.70

ols

-0.65

iannopoulos

-0.62

 Caesar

-0.61

avin

-0.61

Orc

-0.60

 suscept

-0.59

 Geological

-0.59

CV

-0.58

POSITIVE LOGITS

posts

1.31

 accomplished

0.94

keepers

0.93

setting

0.87

goal

0.87

 goal

0.86

 Goal

0.83

post

0.83

ims

0.83

Goal

0.83

Activations Density 0.072%

instances of the word "goal"

references to objectives or goals in various contexts

No Comments

No Known Activations