INDEX

Explanations

phrases indicating a central theme or main point being discussed

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a conclusion or summarization

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

digy

-0.82

#$

-0.76

rouse

-0.70

 Machina

-0.69

ulton

-0.67

xtap

-0.67

inen

-0.65

olkien

-0.64

Footnote

-0.64

sylv

-0.64

POSITIVE LOGITS

 stairs

0.99

stairs

0.96

graded

0.94

river

0.94

grading

0.83

 sidx

0.80

 knees

0.73

grades

0.71

 crashing

0.71

vote

0.71

Activations Density 0.021%

phrases indicating a central theme or main point being discussed

phrases that indicate a conclusion or summarization

No Comments

No Known Activations