INDEX

Explanations

terms related to analysis or critique

oai_token-act-pair · gpt-3.5-turbo

instances of commentary or analysis 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

hene

-0.74

Ī

-0.69

AppData

-0.67

successful

-0.65

quer

-0.63

requ

-0.62

gat

-0.62

rows

-0.61

rect

-0.60

alloc

-0.60

POSITIVE LOGITS

 commentary

3.99

 Commentary

2.45

 commentator

1.79

 commentators

1.74

 narration

1.57

 comment

1.52

 satire

1.46

 Comment

1.46

 critique

1.38

comment

1.35

Activations Density 0.010%

terms related to analysis or critique

instances of commentary or analysis in various contexts

No Comments

No Known Activations