INDEX

Explanations

references to transformations or changes

oai_token-act-pair · gpt-3.5-turbo

elements of surreal or absurd situations in narratives

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

PTS

-0.74

ilitation

-0.69

 consolidated

-0.69

 consolidation

-0.68

ructure

-0.68

isSpecialOrderable

-0.67

IPS

-0.67

onductor

-0.66

 consolid

-0.66

izons

-0.66

POSITIVE LOGITS

 hilar

1.14

 poop

1.13

 crotch

1.10

 piss

1.09

 boobs

1.07

 dick

1.05

 dudes

1.05

 hilarious

1.04

 jokes

1.04

pants

1.03

Activations Density 2.074%

references to transformations or changes

elements of surreal or absurd situations in narratives

No Comments

No Known Activations