INDEX

Explanations

phrases related to actions or situations

oai_token-act-pair · gpt-3.5-turbo

instances of the article "a" followed by descriptive phrases or actions that indicate various situations or events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anwhile

-0.87

enhagen

-0.72

ilight

-0.72

onge

-0.71

dinand

-0.71

grounds

-0.69

ortium

-0.69

 with

-0.69

itially

-0.68

licts

-0.67

POSITIVE LOGITS

 bang

1.27

 vengeance

1.18

 flick

0.95

 flourish

0.93

 newfound

0.91

 impunity

0.87

vig

0.86

 shrug

0.82

 handshake

0.79

 limp

0.77

Activations Density 0.333%

phrases related to actions or situations

instances of the article "a" followed by descriptive phrases or actions that indicate various situations or events

No Comments

No Known Activations