INDEX

Explanations

phrases introducing reasons or justifications

oai_token-act-pair · gpt-3.5-turbo

phrases that begin with "Given," indicating a presentation of conditions 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

ater

-0.79

oiler

-0.79

ereo

-0.78

jer

-0.77

á

-0.74

imming

-0.74

Prev

-0.72

aird

-0.71

ounters

-0.68

retch

-0.68

POSITIVE LOGITS

stellar

0.73

pend

0.72

McF

0.71

 precedence

0.69

 Gust

0.68

imaru

0.67

rely

0.66

wagen

0.64

 hindsight

0.64

Gri

0.64

Activations Density 0.024%

phrases introducing reasons or justifications

phrases that begin with "Given," indicating a presentation of conditions or situations

No Comments

No Known Activations