INDEX

Explanations

words written in a specific script

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character in text, likely related to the Cyrillic alphabet

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riott

-0.84

icio

-0.74

aido

-0.72

arching

-0.69

anced

-0.69

arios

-0.69

 Pyth

-0.69

urst

-0.66

rament

-0.66

-0.65

POSITIVE LOGITS

Ð¼

1.16

Ð

1.15

Ð½

1.11

Ðº

1.11

Ñı

1.11

ÑĤ

1.10

Ð´

1.10

Ð¸

1.06

Ð²

1.06

Ð»

1.04

Activations Density 0.007%

words written in a specific script

occurrences of a specific character in text, likely related to the Cyrillic alphabet

No Comments

No Known Activations