INDEX

Explanations

phrases related to criticism or critique, often involving a negative judgment or evaluation

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating location or relationships

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

 channels

-0.74

clips

-0.74

items

-0.72

rities

-0.72

ities

-0.69

stories

-0.67

houses

-0.67

rooms

-0.66

pots

-0.65

nces

-0.65

POSITIVE LOGITS

EStreamFrame

0.77

srf

0.70

 Wonderland

0.68

ãĥĺ

0.66

 Scarlet

0.66

 familiarity

0.65

rontal

0.63

itan

0.63

rium

0.61

 righteousness

0.61

Activations Density 0.521%

phrases related to criticism or critique, often involving a negative judgment or evaluation

prepositions and phrases indicating location or relationships

No Comments

No Known Activations