INDEX

Explanations

words related to outcomes or conclusions

oai_token-act-pair · gpt-3.5-turbo

phrases that involve the concept of "ending up" or outcomes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itsch

-0.70

hee

-0.67

esis

-0.62

esome

-0.60

olded

-0.60

thouse

-0.59

 reclaimed

-0.59

htaking

-0.59

dinand

-0.58

 principals

-0.58

POSITIVE LOGITS

angering

1.21

ocrin

1.04

owment

1.03

angers

0.96

 abruptly

0.91

 prematurely

0.90

ocrine

0.88

orses

0.88

 tragically

0.86

orse

0.84

Activations Density 0.034%

words related to outcomes or conclusions

phrases that involve the concept of "ending up" or outcomes

No Comments

No Known Activations