INDEX

Explanations

instances of the word "last", particularly when used to denote finality or timing

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "last" in various contexts

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

cil

-0.67

forced

-0.63

les

-0.62

rus

-0.58

Cra

-0.58

RI

-0.57

rend

-0.56

ervatives

-0.56

 Greens

-0.56

closed

-0.56

POSITIVE LOGITS

è¦ļéĨĴ

0.80

 glance

0.76

ICA

0.73

 ditch

0.72

ãĤ´ãĥ³

0.71

 anten

0.69

å§«

0.68

 veter

0.68

 millenn

0.67

ãĤ¼ãĤ¦ãĤ¹

0.66

Activations Density 0.013%

instances of the word "last", particularly when used to denote finality or timing

the repeated use of the word "last" in various contexts

No Comments

No Known Activations