INDEX

Explanations

words related to strength, effectiveness, and reliable performance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "robust" and its variations, indicating a focus on strength and resilience 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pper

-0.65

Station

-0.63

 clicked

-0.62

 Fever

-0.62

Khe

-0.62

Suc

-0.61

hops

-0.60

 Station

-0.60

Companies

-0.59

avez

-0.59

POSITIVE LOGITS

ly

1.15

ness

1.07

ively

0.99

nesses

0.98

mble

0.91

ament

0.87

ity

0.85

itude

0.85

atility

0.84

edly

0.83

Activations Density 0.014%

words related to strength, effectiveness, and reliable performance

instances of the word "robust" and its variations, indicating a focus on strength and resilience in various contexts

No Comments

No Known Activations