INDEX

Explanations

names of people or characters

oai_token-act-pair · gpt-3.5-turbo

letters or sequences of letters that are heavily featured in context, possibly indicating names or technical terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 choke

-0.67

 bearer

-0.66

 inherit

-0.65

 shoulders

-0.64

 toddlers

-0.62

abetic

-0.61

 parcels

-0.59

 tens

-0.58

 reneg

-0.58

 Standing

-0.57

POSITIVE LOGITS

kaya

0.88

cially

0.78

ãĤ£

0.77

tsky

0.77

iman

0.75

ronics

0.74

oren

0.74

wagen

0.72

ihara

0.71

ue

0.71

Activations Density 0.301%

names of people or characters

letters or sequences of letters that are heavily featured in context, possibly indicating names or technical terms

No Comments

No Known Activations