INDEX

Explanations

words related to extreme cold or freezing temperatures

oai_token-act-pair · gpt-3.5-turbo

terms related to cold or temperature extremes

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

anooga

-0.78

oppable

-0.75

osuke

-0.74

 Holding

-0.71

»Ĵ

-0.70

 mathemat

-0.69

 Azerb

-0.68

edIn

-0.68

alde

-0.68

 livest

-0.68

POSITIVE LOGITS

nuts

0.84

 blister

0.78

ivities

0.75

nut

0.75

 liner

0.74

ppings

0.72

IPP

0.72

bat

0.71

TERN

0.69

bread

0.67

Activations Density 0.043%

words related to extreme cold or freezing temperatures

terms related to cold or temperature extremes

No Comments

No Known Activations