INDEX

Explanations

the word "full" in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "full."

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

Wars

-0.69

ANE

-0.69

 Fever

-0.69

!/

-0.68

errors

-0.67

ukong

-0.65

icho

-0.65

DERR

-0.63

abbit

-0.63

anty

-0.62

POSITIVE LOGITS

 extent

1.09

 complement

1.00

 brunt

0.98

ness

0.92

 frontal

0.92

erton

0.89

hearted

0.88

 fled

0.87

 spectrum

0.86

 blown

0.84

Activations Density 0.020%

the word "full" in various contexts

instances of the word "full."

No Comments

No Known Activations