INDEX

Explanations

trigger words related to growth or increase in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to increases or growth in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

thing

-0.82

mates

-0.73

raid

-0.72

halla

-0.70

atom

-0.67

aries

-0.66

oran

-0.66

rome

-0.64

stones

-0.64

oops

-0.63

POSITIVE LOGITS

 visibility

1.18

 likelihood

1.13

 awareness

1.12

 susceptibility

1.03

 efficiency

1.00

 reliance

0.98

 sensitivity

0.98

 exponentially

0.97

 frequency

0.96

 chances

0.96

Activations Density 0.076%

trigger words related to growth or increase in various contexts

terms related to increases or growth in various contexts

No Comments

No Known Activations