INDEX

Explanations

phrases related to negative events or controversial topics

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the."

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

leeve

-0.72

IFA

-0.67

 ItemLevel

-0.67

Slot

-0.67

iffe

-0.65

click

-0.65

cture

-0.65

oken

-0.63

MK

-0.62

POSITIVE LOGITS

 ensuing

1.35

 resultant

1.24

 resulting

1.19

 accompanying

1.17

 remainder

1.14

 consequ

1.12

 slightest

1.09

 vast

1.06

 latter

1.06

 entire

1.04

Activations Density 0.307%

phrases related to negative events or controversial topics

instances of the word "the."

No Comments

No Known Activations