INDEX

Explanations

references to historical events or contexts

oai_token-act-pair · gpt-3.5-turbo

references to historical events and figures

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

lain

-1.04

ertodd

-1.03

nery

-0.86

liga

-0.80

geon

-0.78

DAQ

-0.75

rette

-0.75

Flow

-0.73

rays

-0.73

BSD

-0.73

POSITIVE LOGITS

orical

0.96

 revision

0.95

 significance

0.94

orically

0.92

 preservation

0.89

 relics

0.86

 heritage

0.83

 context

0.82

 historians

0.81

 inaccur

0.80

Activations Density 0.023%

references to historical events or contexts

references to historical events and figures

No Comments

No Known Activations