INDEX

Explanations

abbreviations and initials used in political contexts

oai_token-act-pair · gpt-3.5-turbo

patterns related to numerical and statistical data

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

 endowed

-0.67

bart

-0.64

 modem

-0.64

ãĤ´

-0.61

ãĥ¼ãĤ¯

-0.60

iste

-0.59

 buzz

-0.56

 safegu

-0.56

 coincide

-0.55

CCP

-0.55

POSITIVE LOGITS

 Forces

0.79

å£«

0.79

atoon

0.72

ULT

0.70

RNA

0.69

outher

0.67

 Eliot

0.67

xual

0.66

Lv

0.66

Activations Density 0.059%

abbreviations and initials used in political contexts

patterns related to numerical and statistical data

No Comments

No Known Activations