INDEX

Explanations

locations or positions of entities in different situations

oai_token-act-pair · gpt-3.5-turbo

actions and states of being described in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ients

-0.87

Enlarge

-0.74

seys

-0.71

isms

-0.69

vertis

-0.67

uum

-0.67

io

-0.66

Ã®

-0.65

advertisement

-0.61

imon

-0.61

POSITIVE LOGITS

 another

0.78

 Drift

0.68

 Glory

0.66

 Lieutenant

0.65

 Carmen

0.65

an

0.64

omething

0.64

 priceless

0.63

 LIFE

0.63

0.62

Activations Density 0.105%

locations or positions of entities in different situations

actions and states of being described in a narrative context

No Comments

No Known Activations