INDEX

Explanations

words related to philosophical and abstract concepts, especially those related to existence and ideology

oai_token-act-pair · gpt-3.5-turbo

concepts related to existential themes and crises

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

maid

-0.84

tower

-0.76

ramid

-0.71

ework

-0.70

OTA

-0.69

urat

-0.68

 Cosponsors

-0.68

ribution

-0.67

 ********************************

-0.67

rera

-0.67

POSITIVE LOGITS

 angst

1.04

ist

0.96

 existential

0.93

 warfare

0.91

ists

0.91

 crisis

0.89

 crises

0.86

etically

0.82

 threat

0.82

 dread

0.81

Activations Density 0.020%

words related to philosophical and abstract concepts, especially those related to existence and ideology

concepts related to existential themes and crises

No Comments

No Known Activations