INDEX

Explanations

words that convey emotions or strong emphasis

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "words."

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

DERR

-0.80

olls

-0.75

izo

-0.72

ramid

-0.71

vy

-0.68

Ã±o

-0.67

awaru

-0.64

roid

-0.62

 cumbers

-0.62

 millenn

-0.62

POSITIVE LOGITS

mith

1.44

 spoken

0.99

 uttered

0.96

terday

0.87

 words

0.86

poons

0.85

speak

0.81

 aloud

0.81

words

0.79

writers

0.79

Activations Density 0.021%

words that convey emotions or strong emphasis

occurrences of the word "words."

No Comments

No Known Activations