INDEX

Explanations

mentions or references to the name "Phil"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Phil" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CLASSIFIED

-0.96

tenance

-0.78

DERR

-0.75

erers

-0.74

eer

-0.68

yrinth

-0.68

GGGG

-0.68

erness

-0.65

ãĥ¼ãĥĨãĤ£

-0.65

 Elves

-0.64

POSITIVE LOGITS

anthrop

1.44

istine

1.36

andering

1.14

adel

1.11

oton

1.10

onen

1.07

harm

1.05

ips

1.02

onite

1.01

ophe

1.01

Activations Density 0.015%

mentions or references to the name "Phil"

mentions of the name "Phil" in various contexts

No Comments

No Known Activations