INDEX

Explanations

phrases related to court proceedings or legal terminologies

oai_token-act-pair · gpt-3.5-turbo

terms related to specific locations or organizations

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

yip

-1.01

ndra

-0.75

iazep

-0.74

 begg

-0.69

ursday

-0.64

arcity

-0.63

 unbeliev

-0.60

 compr

-0.59

pad

-0.59

wo

-0.57

POSITIVE LOGITS

crew

0.84

ption

0.80

INAL

0.79

IED

0.78

Ķ

0.70

etary

0.69

ãĤº

0.69

Emb

0.69

Autom

0.68

Royal

0.67

Activations Density 0.040%

phrases related to court proceedings or legal terminologies

terms related to specific locations or organizations

No Comments

No Known Activations