INDEX

Explanations

words related to deference or postponement

oai_token-act-pair · gpt-3.5-turbo

terms related to postponement or delay

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Reviewer

-0.74

ovych

-0.73

ItemTracker

-0.72

 Passion

-0.71

ARS

-0.70

opher

-0.67

 Milton

-0.67

onica

-0.66

ĨĴ

-0.66

oven

-0.66

POSITIVE LOGITS

 deferred

1.26

 defer

1.09

erred

1.04

 adjud

0.90

minist

0.84

ptive

0.81

itures

0.79

 warr

0.77

 assignments

0.75

 gratification

0.74

Activations Density 0.013%

words related to deference or postponement

terms related to postponement or delay

No Comments

No Known Activations