INDEX

Explanations

words related to Japanese cultural references

oai_token-act-pair · gpt-3.5-turbo

words related to a specific linguistic or cultural context, particularly involving the suffix "ese."

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

ãĥ¼ãĥĨ

-0.84

azine

-0.82

ilater

-0.80

razil

-0.79

 Cumm

-0.74

ihar

-0.74

 Kimber

-0.73

icals

-0.70

alist

-0.69

ific

-0.68

POSITIVE LOGITS

ktop

0.82

uth

0.76

wei

0.75

lect

0.71

heng

0.70

clair

0.69

bones

0.69

userc

0.68

ese

0.68

vers

0.67

Activations Density 0.018%

words related to Japanese cultural references

words related to a specific linguistic or cultural context, particularly involving the suffix "ese."

No Comments

No Known Activations