INDEX

Explanations

mentions of specific social media platforms (Facebook and Twitter) in sentences related to accountability and enforcement

oai_token-act-pair · gpt-3.5-turbo

mentions of social media platforms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 defects

-0.71

 stiffness

-0.71

 toughness

-0.68

 displacement

-0.66

 characteristics

-0.65

hani

-0.65

ãĤ¨ãĥ«

-0.64

 regeneration

-0.64

 remission

-0.64

 unborn

-0.63

POSITIVE LOGITS

Twitter

1.03

 Twitter

1.00

 Gmail

0.96

 Internet

0.94

Google

0.93

Tumblr

0.93

 Pinterest

0.92

 Youtube

0.92

 Google

0.91

 Yahoo

0.91

Activations Density 0.264%

mentions of specific social media platforms (Facebook and Twitter) in sentences related to accountability and enforcement

mentions of social media platforms

No Comments

No Known Activations