INDEX

Explanations

instances of responsibilities related to actions or decisions

oai_token-act-pair · gpt-3.5-turbo

terms related to responsibility and roles 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Guan

-0.47

Dow

-0.46

gr

-0.46

 yourselves

-0.46

 Sark

-0.45

orks

-0.45

 oneself

-0.45

Ã°

-0.45

 Salv

-0.44

endez

-0.44

POSITIVE LOGITS

 counterparts

0.86

 counterpart

0.75

 brethren

0.74

 selves

0.73

 holdings

0.70

 cousin

0.69

 mates

0.69

 buddies

0.68

 predecessors

0.67

 cousins

0.67

Activations Density 0.830%

instances of responsibilities related to actions or decisions

terms related to responsibility and roles in various contexts

No Comments

No Known Activations