INDEX

Explanations

instances of the word "that" where it is followed by a sentence describing a particular situation or condition

oai_token-act-pair · gpt-3.5-turbo

phrases containing the word "that."

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

Ö¼

-0.68

 Procedure

-0.67

ARB

-0.65

 Peaks

-0.64

IDES

-0.63

 Invalid

-0.61

ASE

-0.61

issors

-0.61

 Patient

-0.59

fs

-0.59

POSITIVE LOGITS

 mattered

1.00

 happened

0.86

involved

0.86

together

0.82

 transpired

0.82

ente

0.80

soever

0.79

 happens

0.78

 entails

0.77

sembly

0.75

Activations Density 0.030%

instances of the word "that" where it is followed by a sentence describing a particular situation or condition

phrases containing the word "that."

No Comments

No Known Activations