INDEX

Explanations

words related to locations or names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "ins" in various contexts

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

 compr

-0.69

¥µ

-0.68

¶ħ

-0.67

 Achieve

-0.61

¶æ

-0.59

ebin

-0.59

 Bulgar

-0.59

BIL

-0.58

ļ

-0.58

ļé

-0.58

POSITIVE LOGITS

pection

1.24

piration

1.13

urance

1.10

pect

1.05

anity

1.05

ufficient

1.02

ergic

0.97

piring

0.96

ensitive

0.96

poon

0.92

Activations Density 0.019%

words related to locations or names

occurrences of the substring "ins" in various contexts

No Comments

No Known Activations