INDEX

Explanations

mentions of locations using the abbreviation "Va"

oai_token-act-pair · gpt-3.5-turbo

references to the state of Virginia (Va)

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

matic

-0.84

sticks

-0.80

matically

-0.73

dress

-0.71

blocks

-0.71

worthy

-0.68

 worth

-0.64

coat

-0.64

TRY

-0.63

minded

-0.63

POSITIVE LOGITS

Va

1.05

qua

0.91

uble

0.89

asa

0.89

quez

0.88

Va

0.88

ille

0.86

adal

0.86

aca

0.84

adia

0.82

Activations Density 0.011%

mentions of locations using the abbreviation "Va"

references to the state of Virginia (Va)

No Comments

No Known Activations