INDEX

Explanations

terms related to political or procedural processes

oai_token-act-pair · gpt-3.5-turbo

references to governmental support and public actions

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

 veto

-0.54

ãĤ§

-0.54

nai

-0.51

ãĥĻ

-0.51

oret

-0.50

 AIDS

-0.50

mone

-0.49

urable

-0.49

-)

-0.49

ãĥ£

-0.49

POSITIVE LOGITS

.","

0.87

 challeng

0.83

0.82

.''.

0.81

 withd

0.80

.[

0.80

$.

0.75

.</

0.75

*.

0.73

.<

0.72

Activations Density 1.120%

terms related to political or procedural processes

references to governmental support and public actions

No Comments

No Known Activations