INDEX

Explanations

interesting or noteworthy information

oai_token-act-pair · gpt-3.5-turbo

instances of discovery and encounters with new information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

charge

-0.62

 breat

-0.61

 Getty

-0.61

 consum

-0.60

heed

-0.60

ulum

-0.59

imeters

-0.57

MI

-0.55

stood

-0.55

sis

-0.55

POSITIVE LOGITS

Ļ½

0.77

âĹ¼

0.75

 wondering

0.74

NVIDIA

0.73

igslist

0.73

 noticing

0.71

 anew

0.69

?????-

0.69

EMOTE

0.67

 surpr

0.67

Activations Density 0.248%

interesting or noteworthy information

instances of discovery and encounters with new information

No Comments

No Known Activations