INDEX

Explanations

words related to sports teams, specifically the "Red Sox" and "Blue Jays"

oai_token-act-pair · gpt-3.5-turbo

mentions of professional sports teams, particularly the Boston Red Sox and their rivals

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

Downloadha

-0.84

olkien

-0.80

uador

-0.72

schild

-0.70

ature

-0.68

wards

-0.68

awaru

-0.67

etheless

-0.67

netflix

-0.65

 Ples

-0.65

POSITIVE LOGITS

Sox

1.02

 Bulls

0.89

 Orchestra

0.86

 dynasty

0.80

 Stadium

0.80

 Tigers

0.80

 pitcher

0.77

 Baseball

0.77

 Harbor

0.74

 Racing

0.74

Activations Density 0.012%

words related to sports teams, specifically the "Red Sox" and "Blue Jays"

mentions of professional sports teams, particularly the Boston Red Sox and their rivals

No Comments

No Known Activations