INDEX

Explanations

phrases related to different types of professionals or roles

oai_token-act-pair · gpt-3.5-turbo

nouns related to various professions and social groups

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

tains

-0.72

 Ends

-0.67

Increases

-0.66

Returns

-0.65

 Means

-0.64

 Increases

-0.62

 Fixes

-0.62

;;;;;;;;;;;;

-0.62

 Kills

-0.60

 Causes

-0.60

POSITIVE LOGITS

 weren

1.15

 aren

1.13

are

1.11

 were

1.04

folk

0.95

 seem

0.92

 themselves

0.90

 behaved

0.89

who

0.87

 deserve

0.86

Activations Density 0.358%

phrases related to different types of professionals or roles

nouns related to various professions and social groups

No Comments

No Known Activations