INDEX

Explanations

instances where the action of observing or being observed is described

oai_token-act-pair · gpt-3.5-turbo

instances of the word "observe" and its variations

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

cit

-0.84

gur

-0.80

onz

-0.72

este

-0.72

ayers

-0.71

utm

-0.70

ikuman

-0.70

xit

-0.68

rax

-0.67

recy

-0.67

POSITIVE LOGITS

 observation

0.95

 Observ

0.81

 observations

0.74

uality

0.73

 patterns

0.73

lihood

0.70

 observed

0.69

 observing

0.69

 Patterns

0.66

 observe

0.65

Activations Density 0.021%

instances where the action of observing or being observed is described

instances of the word "observe" and its variations

No Comments

No Known Activations