INDEX

Explanations

mentions of a specific term or phrase containing the letters "Tw"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Tw" in various forms and contexts

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

 PRESS

-0.83

senal

-0.83

HAEL

-0.82

ãĤŃ

-0.80

ãĥ£

-0.75

ãĤ¹ãĥĪ

-0.74

 Cheong

-0.71

QC

-0.65

ãģĤ

-0.65

 è£ıç

-0.62

POSITIVE LOGITS

elve

1.21

enty

1.16

orks

1.09

ipes

1.03

anted

1.02

ither

1.01

ilight

0.99

ipe

0.98

ifty

0.97

ixt

0.97

Activations Density 0.007%

mentions of a specific term or phrase containing the letters "Tw"

occurrences of the word "Tw" in various forms and contexts

No Comments

No Known Activations