INDEX

Explanations

specific verbs and adjectives related to formal designations or classifications

oai_token-act-pair · gpt-3.5-turbo

terms related to official designations and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

perty

-0.63

elin

-0.63

uv

-0.62

vous

-0.62

onse

-0.61

umbn

-0.61

Spread

-0.61

hire

-0.60

otrop

-0.59

abama

-0.58

POSITIVE LOGITS

ifiable

0.74

marked

0.68

phas

0.67

 zones

0.63

ependent

0.63

icut

0.63

 classify

0.63

ocument

0.62

enemy

0.62

 Crit

0.61

Activations Density 0.107%

specific verbs and adjectives related to formal designations or classifications

terms related to official designations and classifications

No Comments

No Known Activations