INDEX

Explanations

words related to significant negative events or conditions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "devastating" and related negative impacts

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

cius

-0.88

ploma

-0.77

cling

-0.68

annis

-0.67

ioch

-0.64

uties

-0.64

uni

-0.63

walk

-0.62

endment

-0.62

Ĭ±

-0.62

POSITIVE LOGITS

ly

1.10

 blow

0.99

 havoc

0.98

 devast

0.85

ãĥ¼ãĥĨ

0.82

 blows

0.82

 devastation

0.80

LY

0.77

 absor

0.76

 wrought

0.75

Activations Density 0.021%

words related to significant negative events or conditions

instances of the word "devastating" and related negative impacts

No Comments

No Known Activations