INDEX

Explanations

verbs related to command or instruction

oai_token-act-pair · gpt-3.5-turbo

specific imperative actions or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

eria

-0.70

catentry

-0.69

etimes

-0.62

 Span

-0.59

 presided

-0.59

erie

-0.59

ylon

-0.58

 span

-0.57

 sqor

-0.57

 wont

-0.56

POSITIVE LOGITS

 ASAP

0.96

dress

0.82

 urgently

0.77

heed

0.76

 theirs

0.72

 THEIR

0.71

ipt

0.70

 Tsukuyomi

0.69

ãĥĥãĥī

0.68

igate

0.67

Activations Density 0.340%

verbs related to command or instruction

specific imperative actions or commands

No Comments

No Known Activations