INDEX

Explanations

adverbs expressing a strong degree, especially those related to opinions or perspectives

oai_token-act-pair · gpt-3.5-turbo

adverbs that indicate a degree of certainty or description

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

psons

-0.76

elsen

-0.70

arta

-0.66

 doorway

-0.66

rule

-0.65

ests

-0.63

 succession

-0.63

pez

-0.62

 Liang

-0.61

 shipment

-0.61

POSITIVE LOGITS

 unpleasant

0.76

 disple

0.74

interesting

0.74

ModLoader

0.72

aste

0.70

odox

0.69

 accommod

0.68

 favourable

0.66

Ã´

0.65

nil

0.65

Activations Density 0.034%

adverbs expressing a strong degree, especially those related to opinions or perspectives

adverbs that indicate a degree of certainty or description

No Comments

No Known Activations