INDEX

Explanations

phrases related to locations or geopolitical entities

oai_token-act-pair · gpt-3.5-turbo

sentence-ending punctuation marks, specifically periods

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

 advoc

-0.92

 challeng

-0.92

 destro

-0.84

 mosqu

-0.78

 glim

-0.77

 withd

-0.77

 nodd

-0.76

 compr

-0.74

onga

-0.73

 predec

-0.72

POSITIVE LOGITS

 Besides

0.99

 Whether

0.97

 Especially

0.96

 They

0.94

Its

0.94

 While

0.93

 Though

0.92

If

0.92

 Whilst

0.90

 Although

0.90

Activations Density 0.393%

phrases related to locations or geopolitical entities

sentence-ending punctuation marks, specifically periods

No Comments

No Known Activations