INDEX

Explanations

words related to justification or exoneration

oai_token-act-pair · gpt-3.5-turbo

terms associated with vindication or justification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pee

-0.86

atomic

-0.67

 Towns

-0.65

gas

-0.65

hops

-0.64

pty

-0.61

nap

-0.61

uyomi

-0.59

gap

-0.59

pmwiki

-0.59

POSITIVE LOGITS

 vind

1.29

ictive

1.08

ication

1.07

icated

0.99

icates

0.97

romeda

0.92

iary

0.88

ortun

0.87

icate

0.87

lehem

0.86

Activations Density 0.010%

words related to justification or exoneration

terms associated with vindication or justification

No Comments

No Known Activations