INDEX

Explanations

the word "the" followed by a specific word or phrase

oai_token-act-pair · gpt-3.5-turbo

frequent occurrences of the word "the"

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

 Chun

-0.77

 Reich

-0.71

 Kurdistan

-0.67

 Chamber

-0.66

 Mafia

-0.63

 desperately

-0.63

Kuh

-0.62

 consolidation

-0.62

 Reconstruction

-0.61

 Schwe

-0.61

POSITIVE LOGITS

1.15

vern

0.98

bsite

0.98

toc

0.97

package

0.95

visible

0.94

bidden

0.94

next

0.94

anmar

0.93

mosp

0.91

Activations Density 0.184%

the word "the" followed by a specific word or phrase

frequent occurrences of the word "the"

No Comments

No Known Activations