INDEX

Explanations

words related to the term "Neuron"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Ne" 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

hips

-0.95

 bearer

-0.86

loo

-0.85

DOWN

-0.84

DragonMagazine

-0.82

AGES

-0.78

REAM

-0.76

ãĥ¼ãĥĨãĤ£

-0.74

cake

-0.72

Ranked

-0.71

POSITIVE LOGITS

arest

1.29

olithic

1.16

verend

1.07

cker

1.02

uron

1.02

braska

1.01

umann

1.00

oliberal

0.98

uter

0.97

utral

0.92

Activations Density 0.017%

words related to the term "Neuron"

occurrences of the term "Ne" in various contexts

No Comments

No Known Activations