INDEX

Explanations

Gy-related terms or references

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "Gy" and related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Hurricanes

-0.81

ortium

-0.79

éĹĺ

-0.78

 Dragonbound

-0.71

ACTED

-0.71

 PowerPoint

-0.69

 Wonderland

-0.68

swick

-0.67

IBLE

-0.67

byter

-0.67

POSITIVE LOGITS

psy

1.35

Gy

1.13

rosc

1.03

Gy

0.94

romy

0.92

roid

0.90

vette

0.88

ro

0.88

nec

0.88

ota

0.87

Activations Density 0.016%

Gy-related terms or references

occurrences of the abbreviation "Gy" and related terms

No Comments

No Known Activations