INDEX

Explanations

mentions of the name "Johns Hopkins."

oai_token-act-pair · gpt-3.5-turbo

references to Johns Hopkins University and its associated individuals

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

gered

-0.86

PsyNetMessage

-0.74

opsis

-0.71

cing

-0.71

 awoken

-0.69

ffen

-0.67

razil

-0.65

ptions

-0.65

 Saddam

-0.65

jad

-0.64

POSITIVE LOGITS

 Hopkins

1.25

hip

0.97

kinson

0.91

kins

0.89

ley

0.81

bay

0.80

endish

0.79

 Landing

0.78

nown

0.77

erenn

0.76

Activations Density 0.021%

mentions of the name "Johns Hopkins."

references to Johns Hopkins University and its associated individuals

No Comments

No Known Activations