INDEX

Explanations

occurrences of the word "guards"

oai_token-act-pair · gpt-3.5-turbo

references to guards 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥ£

-0.76

à¤

-0.75

NOT

-0.72

BLE

-0.70

 Scotia

-0.69

CAST

-0.68

astical

-0.66

GET

-0.63

 Lakes

-0.62

thritis

-0.62

POSITIVE LOGITS

 guarding

1.06

maid

1.05

 guards

1.03

men

1.00

andowski

0.97

hip

0.92

guards

0.92

 Guards

0.87

 guarded

0.83

 stationed

0.80

Activations Density 0.013%

occurrences of the word "guards"

references to guards in various contexts

No Comments

No Known Activations