INDEX

Explanations

questions about the reasoning behind decisions or actions

oai_token-act-pair · gpt-3.5-turbo

questions and inquiries related to actions and decisions

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

bits

-0.72

abase

-0.70

 taxp

-0.66

orage

-0.65

tips

-0.63

ource

-0.61

icing

-0.60

ributed

-0.59

oret

-0.58

 SHALL

-0.58

POSITIVE LOGITS

 such

0.77

such

0.72

 chose

0.68

 intrusion

0.68

 fateful

0.67

so

0.65

 abruptly

0.62

 existence

0.61

 abrupt

0.61

 chosen

0.61

Activations Density 0.415%

questions about the reasoning behind decisions or actions

questions and inquiries related to actions and decisions

No Comments

No Known Activations