INDEX

Explanations

translations or mentions of translation related activities

oai_token-act-pair · gpt-3.5-turbo

references to translations and the process of translating texts

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

ndra

-0.90

--+

-0.87

ookie

-0.81

addock

-0.81

oeuv

-0.81

awks

-0.79

olls

-0.79

achine

-0.76

Â¯Â¯

-0.75

cffff

-0.73

POSITIVE LOGITS

 translation

1.17

 translations

1.11

 transl

1.09

 translator

1.06

 Translation

1.00

 translated

0.96

translation

0.92

 subtitles

0.89

language

0.83

 interpreter

0.83

Activations Density 0.020%

translations or mentions of translation related activities

references to translations and the process of translating texts

No Comments

No Known Activations