INDEX

Explanations

phrases indicating willingness or readiness

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate willingness or readiness to take action

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Compass

-0.82

////////////////////////////////

-0.73

Recommended

-0.72

alia

-0.69

DAQ

-0.67

lights

-0.67

availability

-0.67

Lear

-0.66

Wan

-0.64

nutrition

-0.64

POSITIVE LOGITS

 accept

1.23

 sacrifice

1.23

 tolerate

1.11

 embrace

1.10

 negotiate

1.09

 admit

1.08

 commit

1.08

 undertake

1.07

 cooperate

1.06

 concede

1.05

Activations Density 0.081%

phrases indicating willingness or readiness

phrases that indicate willingness or readiness to take action

No Comments

No Known Activations