INDEX

Explanations

phrases containing the word "described as"

oai_token-act-pair · gpt-3.5-turbo

phrases that involve describing or characterizing something

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

ersen

-0.69

OTAL

-0.66

scene

-0.64

LS

-0.63

ramids

-0.63

rene

-0.63

rol

-0.62

heastern

-0.61

oller

-0.61

itous

-0.61

POSITIVE LOGITS

 follows

0.96

pires

0.95

 well

0.83

 opposed

0.82

criptions

0.82

 belonging

0.81

pired

0.81

ylum

0.78

phy

0.76

pire

0.75

Activations Density 0.129%

phrases containing the word "described as"

phrases that involve describing or characterizing something

No Comments

No Known Activations