INDEX

Explanations

definitions

oai_token-act-pair · gpt-3.5-turbo

definitions or descriptions of terms and concepts

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

 Legions

-0.71

 Universities

-0.69

 Surve

-0.65

 lines

-0.65

 directions

-0.65

 exchanges

-0.63

luster

-0.63

 routes

-0.62

 Accounts

-0.61

 Elves

-0.61

POSITIVE LOGITS

ogram

0.80

 ordinarily

0.77

pload

0.75

typically

0.74

agraph

0.74

ritic

0.73

 necessarily

0.73

DonaldTrump

0.71

nai

0.70

 inherently

0.69

Activations Density 0.345%

definitions

definitions or descriptions of terms and concepts

No Comments

No Known Activations