INDEX

Explanations

instances of the word "observed" in the text

oai_token-act-pair · gpt-3.5-turbo

instances or mentions of the word "observed" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

gur

-0.81

venge

-0.80

onz

-0.78

por

-0.76

nec

-0.73

ergy

-0.72

recy

-0.71

email

-0.68

rax

-0.68

neg

-0.67

POSITIVE LOGITS

 observed

1.03

 observation

0.87

ĸļ

0.84

 observing

0.82

 observations

0.82

 observable

0.78

 observe

0.77

 Observ

0.76

 patterns

0.74

 observes

0.73

Activations Density 0.008%

instances of the word "observed" in the text

instances or mentions of the word "observed" in various contexts

No Comments

No Known Activations