INDEX

Explanations

phrases related to revealing information or secrets

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "reveal" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ovie

-0.79

ÃĥÃĤ

-0.76

ortunately

-0.71

tem

-0.69

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.68

hovah

-0.67

 subur

-0.67

ÃĥÃĤÃĥÃĤ

-0.67

anwhile

-0.64

irez

-0.63

POSITIVE LOGITS

 reveal

1.05

 reveals

0.91

ittal

0.79

 discl

0.79

ysis

0.78

advertisement

0.76

 Reve

0.76

 unveil

0.75

 revealing

0.75

reve

0.74

Activations Density 0.010%

phrases related to revealing information or secrets

occurrences of the word "reveal" in various contexts

No Comments

No Known Activations