INDEX

Explanations

proper names starting with "Ren" and followed by a high numeric value

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the name "Ren" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

stakes

-0.84

HAEL

-0.75

OOL

-0.71

Ö¼

-0.69

 Antar

-0.68

 NETWORK

-0.68

milo

-0.68

 Ø§ÙĦ

-0.66

=-=-

-0.66

trak

-0.65

POSITIVE LOGITS

unciation

1.12

issance

1.10

unci

1.06

ovation

1.05

aming

0.94

emy

0.93

ault

0.91

ouncing

0.90

owned

0.89

ochet

0.89

Activations Density 0.010%

proper names starting with "Ren" and followed by a high numeric value

the occurrences of the name "Ren" in the text

No Comments

No Known Activations