INDEX

Explanations

references to people appearing in specific outfits or settings

oai_token-act-pair · gpt-3.5-turbo

occurrences of the preposition "in"

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

 incumb

-0.94

-0.70

 learners

-0.68

 convol

-0.67

 employers

-0.67

llor

-0.64

ens

-0.62

rw

-0.61

%%

-0.60

 lodged

-0.60

POSITIVE LOGITS

 lieu

1.09

animate

1.06

 spite

1.06

appropriately

1.05

 relation

1.03

strument

1.03

clus

1.02

 situ

1.02

 conjunction

1.01

effect

1.01

Activations Density 0.365%

references to people appearing in specific outfits or settings

occurrences of the preposition "in"

No Comments

No Known Activations