INDEX

Explanations

words related to prediction or warning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fore" 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 @ 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

BuyableInstoreAndOnline

-0.84

REDACTED

-0.79

RED

-0.77

IRO

-0.73

å°Ĩ

-0.73

 Stain

-0.70

OPLE

-0.67

Ou

-0.66

 Franks

-0.65

 Shed

-0.63

POSITIVE LOGITS

nsics

1.09

shadow

1.07

warn

1.02

told

1.01

father

1.01

warning

0.99

 fore

0.97

runner

0.97

sight

0.96

shore

0.95

Activations Density 0.007%

words related to prediction or warning

instances of the word "fore" in various contexts

No Comments

No Known Activations