INDEX

Explanations

specific locations within a setting or environment

oai_token-act-pair · gpt-3.5-turbo

references to characters and elements related to storytelling and characterization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 mathemat

-0.65

 diplom

-0.63

urations

-0.61

 accordingly

-0.60

clusively

-0.60

 respectively

-0.59

theless

-0.59

 counterparts

-0.58

 unden

-0.58

 attRot

-0.57

POSITIVE LOGITS

 fame

0.81

 whom

0.70

itaire

0.67

pires

0.65

etter

0.62

hid

0.61

elight

0.61

edin

0.60

oto

0.59

iHUD

0.59

Activations Density 0.641%

specific locations within a setting or environment

references to characters and elements related to storytelling and characterization

No Comments

No Known Activations