INDEX

Explanations

timestamps in the text that indicate when the information was last updated

oai_token-act-pair · gpt-3.5-turbo

various mentions of updates or revisions in content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ardless

-0.82

esm

-0.73

Js

-0.73

ohm

-0.73

rarily

-0.72

vernment

-0.68

gravity

-0.68

ankind

-0.67

plin

-0.66

apesh

-0.65

POSITIVE LOGITS

 Coverage

0.74

daily

0.67

 Date

0.67

 Mara

0.67

 Dates

0.66

Equ

0.65

 VERS

0.64

 Effective

0.64

irement

0.64

 version

0.63

Activations Density 0.021%

timestamps in the text that indicate when the information was last updated

various mentions of updates or revisions in content

No Comments

No Known Activations