INDEX

Explanations

phrases expressing pride or proud feelings

oai_token-act-pair · gpt-3.5-turbo

phrases expressing pride or achievement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.75

resistant

-0.74

scan

-0.66

problem

-0.65

ET

-0.65

bars

-0.64

uto

-0.63

 phased

-0.62

 modes

-0.62

interrupted

-0.61

POSITIVE LOGITS

 accomplishments

0.78

¥µ

0.78

 accomplishment

0.77

0.76

clus

0.73

mberg

0.71

¥

0.69

owship

0.68

 Magical

0.66

 heroism

0.66

Activations Density 0.084%

phrases expressing pride or proud feelings

phrases expressing pride or achievement

No Comments

No Known Activations