INDEX

Explanations

words related to unusual occurrences or situations

oai_token-act-pair · gpt-3.5-turbo

references to unusual or peculiar events and oddities

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

 spons

-0.77

heid

-0.70

 adequate

-0.69

 uncond

-0.67

ederation

-0.65

SPA

-0.63

 exhausted

-0.62

earchers

-0.62

IDA

-0.61

 shoulders

-0.61

POSITIVE LOGITS

 trivia

0.80

 Clown

0.70

iquid

0.69

occ

0.68

 knots

0.68

etheless

0.67

 Balk

0.66

 twists

0.65

 coincidence

0.64

 Monaco

0.63

Activations Density 0.366%

words related to unusual occurrences or situations

references to unusual or peculiar events and oddities

No Comments

No Known Activations