INDEX

Explanations

phrases indicating a future time or sequence of events

oai_token-act-pair · gpt-3.5-turbo

references to temporal markers or specific times in the narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

afety

-0.87

-0.78

Plot

-0.72

ãĥ´

-0.72

 Container

-0.67

tnc

-0.66

 Sweep

-0.66

minecraft

-0.66

 Simpl

-0.66

utra

-0.65

POSITIVE LOGITS

imester

0.75

ABE

0.71

 wiser

0.68

isode

0.68

 sidx

0.68

headers

0.68

 arrive

0.67

 recons

0.66

leases

0.64

aptic

0.63

Activations Density 0.140%

phrases indicating a future time or sequence of events

references to temporal markers or specific times in the narrative

No Comments

No Known Activations