INDEX

Explanations

references to different potential results or consequences

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of outcomes and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 brakes

-0.77

ondo

-0.75

yi

-0.72

andise

-0.71

ker

-0.71

sis

-0.66

aps

-0.66

afort

-0.65

udi

-0.65

king

-0.63

POSITIVE LOGITS

 outcome

1.02

 outcomes

0.98

bringer

0.83

 thereof

0.81

romeda

0.72

 Yanuk

0.68

TPPStreamerBot

0.67

 probabilities

0.67

fulness

0.67

 expectancy

0.67

Activations Density 0.020%

references to different potential results or consequences

terms related to the concept of outcomes and their implications

No Comments

No Known Activations