INDEX

Explanations

words related to nerves

oai_token-act-pair · gpt-3.5-turbo

references to the term "nerve" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

laws

-0.88

aneers

-0.79

enhagen

-0.77

ioch

-0.74

advertisement

-0.74

eanor

-0.73

enance

-0.73

enture

-0.71

atchewan

-0.71

Sah

-0.68

POSITIVE LOGITS

 nerve

1.22

 endings

1.06

 nerves

0.88

 fibers

0.82

gas

0.81

 pier

0.78

 wrench

0.77

 stim

0.77

 fibre

0.77

 punch

0.75

Activations Density 0.018%

words related to nerves

references to the term "nerve" in various contexts

No Comments

No Known Activations