INDEX

Explanations

instances where a statement is followed by a conditional "if" clause expressing improvement or hypothetical scenarios

oai_token-act-pair · gpt-3.5-turbo

conditional phrases starting with "if."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

FTWARE

-0.84

STAR

-0.73

isible

-0.69

advertisement

-0.68

holm

-0.66

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.66

ãĥŃ

-0.66

oscopic

-0.65

akia

-0.65

enos

-0.64

POSITIVE LOGITS

fy

0.93

yip

0.87

rame

0.70

 untreated

0.69

soever

0.68

 unchecked

0.68

 landlords

0.66

terday

0.65

rets

0.65

 Kerr

0.64

Activations Density 0.058%

instances where a statement is followed by a conditional "if" clause expressing improvement or hypothetical scenarios

conditional phrases starting with "if."

No Comments

No Known Activations