INDEX

Explanations

words related to investigations or queries

oai_token-act-pair · gpt-3.5-turbo

words related to inquiries and investigations

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

 Depend

-0.75

perm

-0.64

nown

-0.63

 Kinnikuman

-0.63

fall

-0.62

har

-0.61

rome

-0.60

 martyr

-0.59

enburg

-0.59

 Diesel

-0.57

POSITIVE LOGITS

 inquire

1.04

 probing

1.04

iry

1.01

naires

1.00

 Inqu

0.99

 inqu

0.98

isition

0.95

iries

0.94

 inquiry

0.92

 Inquiry

0.85

Activations Density 0.036%

words related to investigations or queries

words related to inquiries and investigations

No Comments

No Known Activations