INDEX

Explanations

terms related to specific geographical locations, specifically focusing on locations in India like Jammu and Kashmir

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographical regions, particularly Jammu and Kashmir

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

ucl

-0.69

tering

-0.68

rigan

-0.65

blocking

-0.63

arette

-0.63

arded

-0.63

ibur

-0.62

lass

-0.62

rine

-0.61

leaders

-0.60

POSITIVE LOGITS

0.90

racuse

0.81

terday

0.81

--+

0.79

ãĥ¼ãĥĨãĤ£

0.75

ï¸

0.74

aneers

0.73

0.72

Ń·

0.72

Ô

0.71

Activations Density 0.108%

terms related to specific geographical locations, specifically focusing on locations in India like Jammu and Kashmir

mentions of specific geographical regions, particularly Jammu and Kashmir

No Comments

No Known Activations