INDEX

Explanations

terms related to government officials and actions, particularly focusing on the Trump administration

oai_token-act-pair · gpt-3.5-turbo

mentions of government administration and officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Ô

-0.70

vill

-0.70

 Mata

-0.70

ystem

-0.69

WN

-0.64

LV

-0.63

 ILCS

-0.63

Spect

-0.62

¿½

-0.62

onga

-0.61

POSITIVE LOGITS

 officials

0.90

 appoint

0.86

 memorandum

0.83

 nominees

0.83

's

0.79

 administration

0.79

 shutdown

0.78

 agencies

0.78

 signaled

0.77

 official

0.76

Activations Density 0.063%

terms related to government officials and actions, particularly focusing on the Trump administration

mentions of government administration and officials

No Comments

No Known Activations