INDEX

Explanations

variations of the word "make."

oai_token-act-pair · gpt-3.5-turbo

words related to creating or producing items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Fram

-0.61

---------

-0.60

 interpreted

-0.59

 oblig

-0.57

 reigning

-0.57

 Vest

-0.57

 notwithstanding

-0.56

Mania

-0.56

hood

-0.56

POSITIVE LOGITS

 sure

1.07

hift

1.01

netflix

0.82

URE

0.79

ä½ľ

0.77

zie

0.75

ulas

0.75

 sense

0.74

fun

0.74

 landfall

0.72

Activations Density 0.153%

variations of the word "make."

words related to creating or producing items

No Comments

No Known Activations