INDEX

Explanations

words and phrases related to programming and technical instructions

oai_token-act-pair · gpt-3.5-turbo

references to the use of "we" in a collaborative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Reviewer

-0.70

 srfAttach

-0.65

Newsletter

-0.65

 Warm

-0.64

Reply

-0.63

Anth

-0.63

 Lover

-0.61

hood

-0.60

 Hole

-0.60

Winged

-0.60

POSITIVE LOGITS

 initialize

1.07

 assume

1.03

'll

1.01

 denote

0.98

 need

0.96

're

0.96

ighed

0.96

aved

0.94

arers

0.93

eding

0.93

Activations Density 0.139%

words and phrases related to programming and technical instructions

references to the use of "we" in a collaborative context

No Comments

No Known Activations