INDEX

Explanations

words related to financial roles or government positions

oai_token-act-pair · gpt-3.5-turbo

terms related to financial or governmental roles, specifically treasurers and accountants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

aston

-0.68

enna

-0.67

bring

-0.66

aque

-0.64

ively

-0.64

AGES

-0.62

 meanings

-0.62

 enthus

-0.61

aps

-0.60

POSITIVE LOGITS

ptroller

0.88

 Treasurer

0.86

 treasurer

0.83

alty

0.77

esses

0.76

bernatorial

0.74

 Rica

0.73

asury

0.73

âĸĳâĸĳ

0.70

nces

0.70

Activations Density 0.016%

words related to financial roles or government positions

terms related to financial or governmental roles, specifically treasurers and accountants

No Comments

No Known Activations