INDEX

Explanations

years mentioned in historical contexts

oai_token-act-pair · gpt-3.5-turbo

specific years in historical 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

EStreamFrame

-0.84

EStream

-0.77

[+]

-0.67

itivity

-0.67

edIn

-0.65

Score

-0.65

 rollout

-0.64

parency

-0.64

 Bounce

-0.64

IUM

-0.63

POSITIVE LOGITS

ixties

0.99

th

0.90

teenth

0.84

-'

0.83

eteenth

0.81

0.79

amaz

0.78

0.76

eenth

0.75

âĸĪâĸĪ

0.74

Activations Density 0.087%

years mentioned in historical contexts

specific years in historical contexts

No Comments

No Known Activations