INDEX

Explanations

words related to language, particularly specific words in various languages

oai_token-act-pair · gpt-3.5-turbo

linguistic terminology and references to languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilyn

-0.75

kefeller

-0.74

ierra

-0.73

 profitability

-0.69

 Armory

-0.68

 wastewater

-0.66

 shutter

-0.64

zanne

-0.64

 fundra

-0.64

ded

-0.63

POSITIVE LOGITS

 pronunciation

0.99

ictionary

0.97

èª

0.92

 spelling

0.90

 abbre

0.88

igraph

0.87

 Dictionary

0.86

acters

0.84

mith

0.84

 meanings

0.82

Activations Density 0.267%

words related to language, particularly specific words in various languages

linguistic terminology and references to languages

No Comments

No Known Activations