INDEX

Explanations

words related to legal terms and procedures

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "l" and other specific letters in varying contexts

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

 Watkins

-0.79

Cot

-0.75

BMC

-0.70

Gap

-0.67

 Gaul

-0.66

Spa

-0.66

 Leopard

-0.65

 Jagu

-0.65

 Library

-0.64

 Mayer

-0.64

POSITIVE LOGITS

actly

1.14

terday

1.12

vernment

1.07

pecially

1.02

ancial

1.02

theless

0.99

viously

0.99

undred

0.98

withstanding

0.97

imately

0.96

Activations Density 0.133%

words related to legal terms and procedures

occurrences of the letter "l" and other specific letters in varying contexts

No Comments

No Known Activations