INDEX

Explanations

mentions of locations or places

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "let"

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

 cumbers

-0.92

 resil

-0.80

manship

-0.71

 tremend

-0.69

ILY

-0.68

BLE

-0.68

DAY

-0.67

ecause

-0.67

 Palestin

-0.66

 holiest

-0.66

POSITIVE LOGITS

tered

1.10

ariat

1.07

ting

1.05

oad

0.95

own

0.93

ters

0.92

icia

0.91

arget

0.89

ocol

0.88

ective

0.86

Activations Density 0.043%

mentions of locations or places

occurrences of the word "let"

No Comments

No Known Activations