INDEX

Explanations

German words with the suffix "-acht"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "acht" and other similar linguistic patterns

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nesota

-0.86

©¶æ

-0.71

criptions

-0.70

pheus

-0.67

perse

-0.67

ĪĴ

-0.65

ĸļ

-0.65

 ubiqu

-0.64

Ĥİ

-0.64

taboola

-0.64

POSITIVE LOGITS

acht

1.02

rop

0.79

lass

0.78

raf

0.78

mann

0.78

 Dive

0.74

avorite

0.74

raft

0.74

Connector

0.73

raph

0.72

Activations Density 0.006%

German words with the suffix "-acht"

occurrences of the word "acht" and other similar linguistic patterns

No Comments

No Known Activations