INDEX

Explanations

references to a specific person, specifically "Sanders."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Sanders."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ocaust

-0.87

ãĥ¼ãĥĨãĤ£

-0.78

obar

-0.77

tyr

-0.74

obe

-0.74

othy

-0.72

ãĥ¼ãĥĨ

-0.71

ogly

-0.71

————

-0.70

onut

-0.69

POSITIVE LOGITS

 Sanders

1.12

 Supporters

1.01

 supporters

0.95

Sanders

0.92

 Caucus

0.84

 supporter

0.82

 delegates

0.81

0.79

 Bros

0.79

rade

0.77

Activations Density 0.020%

references to a specific person, specifically "Sanders."

mentions of the name "Sanders."

No Comments

No Known Activations