INDEX

Explanations

information related to political parties and statistics

oai_token-act-pair · gpt-3.5-turbo

expressions of trust or mistrust in political 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

 oath

-0.71

 dressing

-0.69

sic

-0.67

 boiler

-0.67

 condone

-0.65

mens

-0.65

 heed

-0.65

sg

-0.64

 pier

-0.64

 vend

-0.64

POSITIVE LOGITS

verages

1.20

Average

1.08

 averages

1.04

 averaged

1.02

Percent

0.96

 Average

0.95

 Percentage

0.93

 averaging

0.92

glomer

0.90

 Adjusted

0.89

Activations Density 0.903%

information related to political parties and statistics

expressions of trust or mistrust in political contexts

No Comments

No Known Activations