INDEX

Explanations

words related to Middle Eastern conflicts or geographical locations

oai_token-act-pair · gpt-3.5-turbo

terms related to ideology and conceptual frameworks

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

enegger

-0.90

wagen

-0.83

iona

-0.83

thening

-0.80

itton

-0.79

ichick

-0.77

ufact

-0.75

dimension

-0.74

cffff

-0.71

lishing

-0.70

POSITIVE LOGITS

lli

0.89

gger

0.87

lla

0.85

llo

0.82

ll

0.80

llan

0.77

ously

0.75

 Dhabi

0.73

 Cors

0.70

ople

0.68

Activations Density 0.022%

words related to Middle Eastern conflicts or geographical locations

terms related to ideology and conceptual frameworks

No Comments

No Known Activations