INDEX

Explanations

phrases related to laws, regulations, and policies

oai_token-act-pair · gpt-3.5-turbo

sentences containing significant statements or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 masterpiece

-0.71

 penn

-0.68

 effortlessly

-0.66

 essentials

-0.66

 feat

-0.65

 loser

-0.65

 flawless

-0.64

ifice

-0.64

 saves

-0.63

 grunt

-0.63

POSITIVE LOGITS

 Specifically

1.17

Specifically

1.03

catentry

0.97

particularly

0.90

untled

0.88

 Particularly

0.88

 discussed

0.87

 Questions

0.86

ussions

0.86

 Concern

0.86

Activations Density 0.765%

phrases related to laws, regulations, and policies

sentences containing significant statements or observations

No Comments

No Known Activations