INDEX

Explanations

terms related to legal and regulatory concepts, such as entrapment

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to various forms of "ent" (such as entertainment, engagement, and arrangement)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Spears

-0.74

å£«

-0.73

 Jenner

-0.72

 Responsibility

-0.67

å§«

-0.66

strap

-0.65

BILITIES

-0.63

enthal

-0.63

BILITY

-0.61

 Accountability

-0.60

POSITIVE LOGITS

renched

1.06

ourage

1.03

inence

0.99

rust

0.98

ailed

0.98

itled

0.93

rench

0.93

ropy

0.91

rained

0.90

uri

0.90

Activations Density 0.014%

terms related to legal and regulatory concepts, such as entrapment

words and phrases related to various forms of "ent" (such as entertainment, engagement, and arrangement)

No Comments

No Known Activations