INDEX

Explanations

words related to downplaying or minimizing something

oai_token-act-pair · gpt-3.5-turbo

words related to belief or disbelief

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chnology

-0.76

office

-0.67

 Detail

-0.66

 Enhancement

-0.64

 Methods

-0.63

LR

-0.61

OTA

-0.61

effects

-0.60

 Fields

-0.60

zzo

-0.59

POSITIVE LOGITS

ieving

1.08

ievers

1.07

ief

1.04

iever

1.02

ichick

1.02

ieve

0.99

le

0.95

oved

0.95

ieved

0.93

ittle

0.90

Activations Density 0.029%

words related to downplaying or minimizing something

words related to belief or disbelief

No Comments

No Known Activations