INDEX

Explanations

names of financial institutions, specifically "Wells Fargo"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Wells" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

eer

-0.79

++++++++++++++++

-0.72

elist

-0.70

eers

-0.70

Agg

-0.67

 elig

-0.66

*/(

-0.66

eering

-0.64

emort

-0.63

 Abyssal

-0.63

POSITIVE LOGITS

 Fargo

1.51

 Wells

1.07

brook

0.88

ocrates

0.86

esley

0.84

orrow

0.83

 Stephens

0.81

oks

0.80

ards

0.77

 Dodd

0.77

Activations Density 0.009%

names of financial institutions, specifically "Wells Fargo"

mentions of the name "Wells" and its variations in various contexts

No Comments

No Known Activations