INDEX

Explanations

mentions of abstract or intangible concepts, particularly related to events or situations

oai_token-act-pair · gpt-3.5-turbo

references to the state of affairs or situations

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

gee

-0.81

bern

-0.77

ISSION

-0.65

iary

-0.64

adia

-0.63

CHR

-0.62

AND

-0.62

sts

-0.61

STER

-0.61

pless

-0.61

POSITIVE LOGITS

 happened

0.95

 happening

0.95

 happen

0.93

 happ

0.85

 transpired

0.84

 happens

0.81

 toget

0.75

 pertaining

0.75

 Happ

0.75

afety

0.74

Activations Density 0.039%

mentions of abstract or intangible concepts, particularly related to events or situations

references to the state of affairs or situations

No Comments

No Known Activations