INDEX

Explanations

words related to aftermath or post-occurring states

oai_token-act-pair · gpt-3.5-turbo

words related to posthumous recognition or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Rivals

-0.68

ONSORED

-0.67

 Brill

-0.65

eth

-0.60

 Judd

-0.59

steen

-0.59

ENG

-0.58

ppo

-0.57

dh

-0.57

ibly

-0.56

POSITIVE LOGITS

umatic

1.00

ocalyptic

0.87

opausal

0.86

ariat

0.84

arcity

0.76

antage

0.74

ension

0.73

lict

0.71

ritic

0.71

roleum

0.71

Activations Density 0.094%

words related to aftermath or post-occurring states

words related to posthumous recognition or events

No Comments

No Known Activations