INDEX

Explanations

instances where something is finally happening or being accomplished

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "finally."

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

 Akin

-0.75

amon

-0.70

quartered

-0.67

lav

-0.65

river

-0.65

icipated

-0.64

 constituencies

-0.64

holders

-0.64

holder

-0.64

maid

-0.63

POSITIVE LOGITS

 reunited

1.09

icably

0.95

 reun

0.89

éĹĺ

0.89

 relent

0.80

 reintrodu

0.79

FTWARE

0.77

icable

0.77

 finally

0.77

 settled

0.76

Activations Density 0.019%

instances where something is finally happening or being accomplished

occurrences of the word "finally."

No Comments

No Known Activations