INDEX

Explanations

phrases related to political figures and actions

oai_token-act-pair · gpt-3.5-turbo

the word "more" and its associated context in discussions related to policy and political commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĥ¼ãĥĨãĤ£

-0.83

ãĤ©

-0.72

 Columb

-0.71

Gum

-0.67

Loc

-0.64

ãĥĨãĤ£

-0.64

 Shining

-0.63

ãĥ¥

-0.62

Rust

-0.59

adapt

-0.59

POSITIVE LOGITS

zbollah

0.81

 confid

0.81

Jr

0.73

 allies

0.72

 aide

0.71

 nominee

0.69

 lashed

0.68

 campaigned

0.67

 strategist

0.67

 staffer

0.66

Activations Density 0.018%

phrases related to political figures and actions

the word "more" and its associated context in discussions related to policy and political commentary

No Comments

No Known Activations