INDEX

Explanations

tech-related terms and brand names

oai_token-act-pair · gpt-3.5-turbo

references to technology companies and their products

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

 lightly

-0.61

 theirs

-0.58

 mandate

-0.58

 determining

-0.58

BILITY

-0.57

FSA

-0.56

 negotiating

-0.56

 Garland

-0.56

 licens

-0.56

 namely

-0.56

POSITIVE LOGITS

amo

0.86

bur

0.84

ango

0.82

osh

0.82

avia

0.82

az

0.81

ona

0.81

onia

0.81

odka

0.80

aza

0.80

Activations Density 0.508%

tech-related terms and brand names

references to technology companies and their products

No Comments

No Known Activations