INDEX

Explanations

governmental actions or decisions

oai_token-act-pair · gpt-3.5-turbo

words related to governmental actions and decisions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

yond

-0.80

cum

-0.69

die

-0.66

cause

-0.63

cell

-0.62

scar

-0.61

Scar

-0.60

arc

-0.60

actual

-0.60

won

-0.60

POSITIVE LOGITS

 unanimously

0.68

 declass

0.63

 appoint

0.63

 indemn

0.61

 Dempsey

0.60

 Bravo

0.59

Zup

0.59

 approving

0.58

 Brady

0.57

 Mattis

0.57

Activations Density 0.882%

governmental actions or decisions

words related to governmental actions and decisions

No Comments

No Known Activations