INDEX

Explanations

phrases indicating justification or rationale for belief or action

oai_token-act-pair · gpt-3.5-turbo

phrases that express reasons to be optimistic or have hope

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

thumbnails

-0.76

soever

-0.71

ches

-0.67

 Appears

-0.65

DAQ

-0.65

ologies

-0.65

stars

-0.62

 Laksh

-0.62

tle

-0.61

Kru

-0.61

POSITIVE LOGITS

 revisit

1.05

 believe

1.01

 doubt

1.00

 reconsider

0.93

 mistrust

0.93

 distrust

0.90

 disregard

0.90

 pause

0.89

 celebrate

0.89

 rethink

0.88

Activations Density 0.073%

phrases indicating justification or rationale for belief or action

phrases that express reasons to be optimistic or have hope

No Comments

No Known Activations