INDEX

Explanations

the word "Either" indicating a choice between two options

oai_token-act-pair · gpt-3.5-turbo

the word "either" and its contextual usage

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

achus

-0.72

riad

-0.72

appings

-0.72

abor

-0.71

bang

-0.69

pu

-0.69

iliar

-0.68

ouver

-0.67

ultan

-0.66

bul

-0.65

POSITIVE LOGITS

lift

0.73

soever

0.69

 halves

0.65

ħĭ

0.65

 willfully

0.65

Either

0.63

ndra

0.63

llor

0.62

 redistributed

0.62

 Rivals

0.62

Activations Density 0.016%

the word "Either" indicating a choice between two options

the word "either" and its contextual usage

No Comments

No Known Activations