INDEX

Explanations

phrases related to revealing information

oai_token-act-pair · gpt-3.5-turbo

words related to revelatory content or disclosures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 à¨

-0.76

ãĥ¼ãĥĨ

-0.72

Io

-0.69

 admission

-0.69

ocene

-0.68

 Icelandic

-0.68

 è£ıè

-0.67

 Nadu

-0.67

é¾įå

-0.66

 guiActiveUnfocused

-0.63

POSITIVE LOGITS

llers

1.51

lling

1.48

ller

1.36

lled

1.29

cks

1.19

ille

1.09

aters

1.07

ll

1.04

ggie

1.04

aling

1.00

Activations Density 0.051%

phrases related to revealing information

words related to revelatory content or disclosures

No Comments

No Known Activations