INDEX

Explanations

phrases indicating likelihood or predictions about future events

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

words related to potential actions or consequences

oai_token-act-pair · gpt-3.5-turbo

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

Reporting

-0.65

 Managing

-0.62

 Sure

-0.62

checking

-0.60

 Checking

-0.60

ortunately

-0.60

 Advertisement

-0.59

tracks

-0.59

listed

-0.58

 Provided

-0.58

POSITIVE LOGITS

be

1.06

 attract

0.82

 coincide

0.82

 avoid

0.81

 become

0.80

 intensify

0.80

 bring

0.78

 consolidate

0.78

 absorb

0.78

 uphold

0.78

Activations Density 0.077%

phrases indicating likelihood or predictions about future events

words related to potential actions or consequences

No Comments

No Known Activations