INDEX

Explanations

terms related to comparisons or contrasts

oai_token-act-pair · gpt-3.5-turbo

phrases contrasting different viewpoints or sides of an argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

neau

-0.79

Blocks

-0.73

 ILCS

-0.69

ental

-0.68

ga

-0.66

iper

-0.66

chairs

-0.66

Kings

-0.65

 Pens

-0.65

nas

-0.64

POSITIVE LOGITS

 cynicism

0.71

iosyncr

0.68

 secondly

0.68

 implication

0.67

 importantly

0.66

 alternatively

0.65

ifact

0.64

oliath

0.64

 antioxid

0.62

 reck

0.62

Activations Density 0.207%

terms related to comparisons or contrasts

phrases contrasting different viewpoints or sides of an argument

No Comments

No Known Activations