INDEX

Explanations

words related to specific names and locations

oai_token-act-pair · gpt-3.5-turbo

prominent names and locations associated with cultural or social topics

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

theless

-0.73

flush

-0.70

reen

-0.68

orbit

-0.67

utils

-0.65

stock

-0.62

hement

-0.62

porting

-0.61

orically

-0.61

ritz

-0.61

POSITIVE LOGITS

 Edition

0.76

 guiName

0.74

 Collection

0.73

 Apocalypse

0.72

 Awakens

0.70

èĢħ

0.68

 Goddess

0.66

 Statue

0.66

;;;;;;;;;;;;

0.65

 Parables

0.64

Activations Density 0.453%

words related to specific names and locations

prominent names and locations associated with cultural or social topics

No Comments

No Known Activations