INDEX

Explanations

phrases related to negative outcomes or consequences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fire" and its variations 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 @ 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

meric

-0.85

anson

-0.81

sembly

-0.75

sie

-0.74

 Redmond

-0.74

omo

-0.72

 Citizen

-0.71

eston

-0.68

VIDIA

-0.67

 Gutenberg

-0.65

POSITIVE LOGITS

flies

1.13

fly

0.97

lda

0.81

fighter

0.80

proof

0.78

storm

0.77

ricanes

0.75

 hotter

0.74

 extingu

0.73

fighters

0.72

Activations Density 0.016%

phrases related to negative outcomes or consequences

instances of the word "fire" and its variations in various contexts

No Comments

No Known Activations