INDEX

Explanations

references to locations and entities in a formal context

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

terms related to locations and settings

oai_token-act-pair · gpt-3.5-turbo

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

Newsletter

-0.71

Loading

-0.68

nant

-0.66

Products

-0.64

DH

-0.63

earable

-0.63

Hub

-0.62

emade

-0.62

RM

-0.59

Ore

-0.58

POSITIVE LOGITS

arently

0.64

vironment

0.63

clud

0.63

 insistence

0.59

 reckoning

0.59

 imagin

0.59

 interval

0.59

 insertion

0.58

çĶ°

0.58

 Samar

0.58

Activations Density 0.441%

references to locations and entities in a formal context

terms related to locations and settings

No Comments

No Known Activations