INDEX

Explanations

website URLs ending with .com

oai_token-act-pair · gpt-3.5-turbo

occurrences of the domain "com", indicating a focus on commercial or website-related references

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

 governors

-0.72

 Balt

-0.67

 bullies

-0.65

 burgl

-0.65

 progress

-0.64

 robbers

-0.63

 cuts

-0.62

 Goldberg

-0.61

 cosmetic

-0.60

 proced

-0.59

POSITIVE LOGITS

/?

0.96

biz

0.88

lisher

0.88

nw

0.87

pleted

0.87

pletion

0.86

nl

0.85

psons

0.85

lishing

0.84

ibaba

0.82

Activations Density 0.031%

website URLs ending with .com

occurrences of the domain "com", indicating a focus on commercial or website-related references

No Comments

No Known Activations