INDEX

Explanations

mentions of someone earning recognition or rewards for their achievements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "earned" and its variations

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

Not in Any Lists

No Comments

Negative Logits

":["

-0.69

mos

-0.69

adra

-0.68

irez

-0.67

 illum

-0.64

yz

-0.63

issue

-0.62

 Leilan

-0.62

apest

-0.61

 symp

-0.61

POSITIVE LOGITS

 earn

0.92

 earned

0.80

Earn

0.79

 earning

0.78

 laure

0.78

 applause

0.77

hardt

0.76

 Earn

0.74

ãĥ©ãĥ³

0.72

earned

0.72

Activations Density 0.011%

mentions of someone earning recognition or rewards for their achievements

instances of the word "earned" and its variations

No Comments

No Known Activations