INDEX

Explanations

words or phrases related to medical conditions, particularly focused on altered states or conflicts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'c'

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

ĪĴ

-0.95

 Grateful

-0.68

 contagious

-0.68

ãĥĹ

-0.67

 resil

-0.67

Magikarp

-0.66

 Tycoon

-0.65

 juggling

-0.64

 rake

-0.63

Ĥ¬

-0.63

POSITIVE LOGITS

ursor

1.25

redits

1.20

ologne

1.19

isco

1.18

oding

1.18

ourses

1.12

ortex

1.11

rossover

1.09

ursed

1.09

rawl

1.09

Activations Density 0.036%

words or phrases related to medical conditions, particularly focused on altered states or conflicts

occurrences of the letter 'c'

No Comments

No Known Activations