INDEX

Explanations

mentions of discussions or negotiations

oai_token-act-pair · gpt-3.5-turbo

references to negotiations or discussions, specifically related to peace talks

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

olls

-0.77

ross

-0.68

lesi

-0.63

negie

-0.61

Lake

-0.61

ously

-0.61

clair

-0.59

 mans

-0.58

 exaggerated

-0.58

gary

-0.58

POSITIVE LOGITS

pace

0.92

 negotiations

0.91

paces

0.82

 negotiation

0.78

hops

0.78

afety

0.77

cape

0.76

 negotiator

0.76

 Talks

0.75

 negotiators

0.74

Activations Density 0.038%

mentions of discussions or negotiations

references to negotiations or discussions, specifically related to peace talks

No Comments

No Known Activations