INDEX

Explanations

information about processes or methods

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "how."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Tanz

-0.67

isher

-0.66

lehem

-0.62

 Goth

-0.59

 Grail

-0.57

amen

-0.57

)]

-0.57

agonists

-0.57

 Mercenary

-0.56

wear

-0.56

POSITIVE LOGITS

soever

1.05

ever

0.88

HCR

0.81

beit

0.80

ells

0.77

ling

0.75

ls

0.75

 much

0.74

 exactly

0.73

 MUCH

0.71

Activations Density 0.085%

information about processes or methods

occurrences of the word "how."

No Comments

No Known Activations