INDEX

Explanations

phrases starting with 'We' or similar pronouns

oai_token-act-pair · gpt-3.5-turbo

pronouns indicating personal or collective perspectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Leilan

-0.64

ãĥ¼ãĥĨ

-0.61

 goto

-0.53

 outwe

-0.51

 Constantin

-0.50

 cradle

-0.50

ioxide

-0.49

 Reef

-0.46

 reef

-0.46

sylv

-0.46

POSITIVE LOGITS

jriwal

0.75

estine

0.62

sect

0.58

vernment

0.58

Dat

0.58

anmar

0.57

Bus

0.57

anyahu

0.56

NetMessage

0.55

agar

0.55

Activations Density 0.228%

phrases starting with 'We' or similar pronouns

pronouns indicating personal or collective perspectives

No Comments

No Known Activations