INDEX

Explanations

acronyms related to information technology (IT)

oai_token-act-pair · gpt-3.5-turbo

references to 'Information Systems' across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ruciating

-0.77

¥ŀ

-0.74

è¦ļéĨĴ

-0.72

ãĥĥãĥĪ

-0.70

uster

-0.68

itbart

-0.67

ojure

-0.66

 crates

-0.65

cakes

-0.65

clad

-0.65

POSITIVE LOGITS

TRY

1.10

HER

1.08

BN

1.06

earch

1.04

SON

1.02

KI

1.00

SI

0.99

CO

0.99

PLAY

0.98

IK

0.98

Activations Density 0.012%

acronyms related to information technology (IT)

references to 'Information Systems' across various contexts

No Comments

No Known Activations