INDEX

Explanations

terms related to a particular entity or concept denoted by the letter "R"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "R"

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

terson

-0.70

 Nieto

-0.66

 Dolphin

-0.65

CPR

-0.64

 Coral

-0.64

 Speedway

-0.63

 quantity

-0.63

ãĥ¼ãĥĨãĤ£

-0.63

 Pose

-0.63

 âĵĺ

-0.63

POSITIVE LOGITS

ansom

1.32

haps

1.26

outine

1.24

ascal

1.23

senal

1.23

attle

1.13

ifles

1.12

ICH

1.12

otten

1.11

ushing

1.11

Activations Density 0.044%

terms related to a particular entity or concept denoted by the letter "R"

occurrences of the letter "R"

No Comments

No Known Activations